< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 439 in Layer 3

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: 2.5309. Min Range: -2.5309

Max Act: 2.5309. Min Act: -0.1700

Data Index: 6144627 (Open Web Text)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.4890. Min Act: -0.1700

Data Index: 4610083 (Open Web Text)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.4244. Min Act: -0.1700

Data Index: 2389001 (Open Web Text)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.4518. Min Act: -0.1700

Data Index: 6099623 (Open Web Text)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.4620. Min Act: -0.1700

Data Index: 4693445 (Open Web Text)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.4201. Min Act: -0.1700

Data Index: 7003331 (Open Web Text)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.4157. Min Act: -0.1700

Data Index: 2817351 (Open Web Text)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.4039. Min Act: -0.1700

Data Index: 7213607 (Open Web Text)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.4139. Min Act: -0.1700

Data Index: 4320187 (Open Web Text)

Max Activating Token Index: 458

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.4106. Min Act: -0.1700

Data Index: 260667 (Open Web Text)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3715. Min Act: -0.1700

Data Index: 4003463 (Open Web Text)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3653. Min Act: -0.1700

Data Index: 8220981 (Open Web Text)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3757. Min Act: -0.1700

Data Index: 2258876 (Open Web Text)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3805. Min Act: -0.1700

Data Index: 3527921 (Open Web Text)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3804. Min Act: -0.1700

Data Index: 6429239 (Open Web Text)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3656. Min Act: -0.1700

Data Index: 7074249 (Open Web Text)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3657. Min Act: -0.1700

Data Index: 6910577 (Open Web Text)

Max Activating Token Index: 395

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3628. Min Act: -0.1700

Data Index: 4975741 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3648. Min Act: -0.1700

Data Index: 5928575 (Open Web Text)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.5309. Min Range: -2.5309

Max Act: 2.3525. Min Act: -0.1700

Data Index: 2059810 (Open Web Text)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #19