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

Dataset: Open Web Text

Neuron 1402 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: 3.3918. Min Range: -3.3918

Max Act: 3.3918. Min Act: -0.1700

Data Index: 1808677 (Open Web Text)

Max Activating Token Index: 495

Text #1

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.3408. Min Act: -0.1700

Data Index: 3432129 (Open Web Text)

Max Activating Token Index: 685

Text #2

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2992. Min Act: -0.1700

Data Index: 3067912 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2734. Min Act: -0.1700

Data Index: 325792 (Open Web Text)

Max Activating Token Index: 522

Text #4

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2371. Min Act: -0.1700

Data Index: 7687638 (Open Web Text)

Max Activating Token Index: 951

Text #5

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2428. Min Act: -0.1700

Data Index: 7420848 (Open Web Text)

Max Activating Token Index: 556

Text #6

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2217. Min Act: -0.1700

Data Index: 3411877 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2278. Min Act: -0.1700

Data Index: 3501265 (Open Web Text)

Max Activating Token Index: 736

Text #8

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2332. Min Act: -0.1700

Data Index: 464059 (Open Web Text)

Max Activating Token Index: 574

Text #9

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2040. Min Act: -0.1700

Data Index: 6142224 (Open Web Text)

Max Activating Token Index: 204

Text #10

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2117. Min Act: -0.1700

Data Index: 7032687 (Open Web Text)

Max Activating Token Index: 754

Text #11

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.2069. Min Act: -0.1700

Data Index: 8389559 (Open Web Text)

Max Activating Token Index: 843

Text #12

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.1845. Min Act: -0.1700

Data Index: 5350568 (Open Web Text)

Max Activating Token Index: 860

Text #13

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.1572. Min Act: -0.1700

Data Index: 3432131 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.1481. Min Act: -0.1700

Data Index: 5260862 (Open Web Text)

Max Activating Token Index: 880

Text #15

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.1515. Min Act: -0.1700

Data Index: 5212808 (Open Web Text)

Max Activating Token Index: 427

Text #16

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.1620. Min Act: -0.1700

Data Index: 1597904 (Open Web Text)

Max Activating Token Index: 762

Text #17

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.1394. Min Act: -0.1700

Data Index: 891347 (Open Web Text)

Max Activating Token Index: 767

Text #18

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.1557. Min Act: -0.1700

Data Index: 333022 (Open Web Text)

Max Activating Token Index: 877

Text #19

Max Range: 3.3918. Min Range: -3.3918

Max Act: 3.1226. Min Act: -0.1700

Data Index: 3457512 (Open Web Text)

Max Activating Token Index: 897