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

Dataset: Open Web Text

Neuron 2421 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: 3.8359. Min Range: -3.8359

Max Act: 3.8359. Min Act: -0.1700

Data Index: 8392591 (Open Web Text)

Max Activating Token Index: 144

Text #1

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.4705. Min Act: -0.1700

Data Index: 4871018 (Open Web Text)

Max Activating Token Index: 981

Text #2

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3995. Min Act: -0.1700

Data Index: 7477044 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.4294. Min Act: -0.1700

Data Index: 6588281 (Open Web Text)

Max Activating Token Index: 673

Text #4

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.4237. Min Act: -0.1700

Data Index: 3454654 (Open Web Text)

Max Activating Token Index: 634

Text #5

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3976. Min Act: -0.1700

Data Index: 7258333 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3956. Min Act: -0.1700

Data Index: 2099786 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3958. Min Act: -0.1700

Data Index: 4346094 (Open Web Text)

Max Activating Token Index: 188

Text #8

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.4038. Min Act: -0.1700

Data Index: 7266882 (Open Web Text)

Max Activating Token Index: 368

Text #9

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3796. Min Act: -0.1700

Data Index: 1843347 (Open Web Text)

Max Activating Token Index: 485

Text #10

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3546. Min Act: -0.1700

Data Index: 6447349 (Open Web Text)

Max Activating Token Index: 817

Text #11

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3457. Min Act: -0.1700

Data Index: 8217842 (Open Web Text)

Max Activating Token Index: 350

Text #12

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3538. Min Act: -0.1700

Data Index: 5141465 (Open Web Text)

Max Activating Token Index: 319

Text #13

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3429. Min Act: -0.1700

Data Index: 302410 (Open Web Text)

Max Activating Token Index: 936

Text #14

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3478. Min Act: -0.1700

Data Index: 6211269 (Open Web Text)

Max Activating Token Index: 668

Text #15

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3278. Min Act: -0.1700

Data Index: 4926488 (Open Web Text)

Max Activating Token Index: 897

Text #16

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3024. Min Act: -0.1700

Data Index: 3516566 (Open Web Text)

Max Activating Token Index: 524

Text #17

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3455. Min Act: -0.1700

Data Index: 2283810 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3351. Min Act: -0.1700

Data Index: 6447043 (Open Web Text)

Max Activating Token Index: 312

Text #19

Max Range: 3.8359. Min Range: -3.8359

Max Act: 3.3312. Min Act: -0.1700

Data Index: 3085553 (Open Web Text)

Max Activating Token Index: 171