< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1854 in Layer 6

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: 2.5553. Min Range: -2.5553

Max Act: 2.5553. Min Act: -0.1700

Data Index: 7751964 (Open Web Text)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.5337. Min Act: -0.1700

Data Index: 4061509 (Open Web Text)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.5201. Min Act: -0.1700

Data Index: 5039858 (Open Web Text)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.5302. Min Act: -0.1700

Data Index: 7072722 (Open Web Text)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.5172. Min Act: -0.1700

Data Index: 5814613 (Open Web Text)

Max Activating Token Index: 165

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4901. Min Act: -0.1700

Data Index: 226622 (Open Web Text)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4981. Min Act: -0.1700

Data Index: 255320 (Open Web Text)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.5048. Min Act: -0.1700

Data Index: 685181 (Open Web Text)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4972. Min Act: -0.1700

Data Index: 1365658 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.5064. Min Act: -0.1700

Data Index: 8233911 (Open Web Text)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.5156. Min Act: -0.1700

Data Index: 5569338 (Open Web Text)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4623. Min Act: -0.1700

Data Index: 6402531 (Open Web Text)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4653. Min Act: -0.1700

Data Index: 2785201 (Open Web Text)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4549. Min Act: -0.1700

Data Index: 4993233 (Open Web Text)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4457. Min Act: -0.1700

Data Index: 5588159 (Open Web Text)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4622. Min Act: -0.1700

Data Index: 6259411 (Open Web Text)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4481. Min Act: -0.1700

Data Index: 2448465 (Open Web Text)

Max Activating Token Index: 97

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4257. Min Act: -0.1700

Data Index: 7353959 (Open Web Text)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4036. Min Act: -0.1700

Data Index: 1411604 (Open Web Text)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.5553. Min Range: -2.5553

Max Act: 2.4021. Min Act: -0.1700

Data Index: 5992710 (Open Web Text)

Max Activating Token Index: 371

Click toggle to see full text

Truncated

Full Text #19