< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1286 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.6560. Min Act: -0.1700

Data Index: 4351806 (Open Web Text)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.6522. Min Act: -0.1700

Data Index: 2696061 (Open Web Text)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.6558. Min Act: -0.1700

Data Index: 8333718 (Open Web Text)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.6307. Min Act: -0.1700

Data Index: 5096170 (Open Web Text)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.6380. Min Act: -0.1700

Data Index: 5118963 (Open Web Text)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5531. Min Act: -0.1700

Data Index: 8697777 (Open Web Text)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5836. Min Act: -0.1700

Data Index: 3926488 (Open Web Text)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5791. Min Act: -0.1700

Data Index: 7340184 (Open Web Text)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5763. Min Act: -0.1700

Data Index: 1470799 (Open Web Text)

Max Activating Token Index: 511

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5565. Min Act: -0.1700

Data Index: 4586478 (Open Web Text)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5648. Min Act: -0.1700

Data Index: 5138788 (Open Web Text)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5613. Min Act: -0.1700

Data Index: 5496220 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5386. Min Act: -0.1700

Data Index: 4730254 (Open Web Text)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5497. Min Act: -0.1700

Data Index: 3627143 (Open Web Text)

Max Activating Token Index: 758

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5154. Min Act: -0.1700

Data Index: 4836682 (Open Web Text)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5224. Min Act: -0.1700

Data Index: 7868235 (Open Web Text)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5248. Min Act: -0.1700

Data Index: 2400112 (Open Web Text)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.4747. Min Act: -0.1700

Data Index: 8614992 (Open Web Text)

Max Activating Token Index: 960

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.4750. Min Act: -0.1700

Data Index: 1739148 (Open Web Text)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.4947. Min Act: -0.1700

Data Index: 5074593 (Open Web Text)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #19