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

Dataset: Open Web Text

Neuron 672 in Layer 5

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: 4.1596. Min Range: -4.1596

Max Act: 4.1596. Min Act: -0.1700

Data Index: 1930843 (Open Web Text)

Max Activating Token Index: 674

Text #1

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.9148. Min Act: -0.1700

Data Index: 1914017 (Open Web Text)

Max Activating Token Index: 284

Text #2

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.8139. Min Act: -0.1700

Data Index: 7741038 (Open Web Text)

Max Activating Token Index: 532

Text #3

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.7320. Min Act: -0.1700

Data Index: 973904 (Open Web Text)

Max Activating Token Index: 705

Text #4

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6628. Min Act: -0.1700

Data Index: 5876920 (Open Web Text)

Max Activating Token Index: 118

Text #5

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6621. Min Act: -0.1700

Data Index: 253513 (Open Web Text)

Max Activating Token Index: 31

Text #6

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6708. Min Act: -0.1700

Data Index: 7999096 (Open Web Text)

Max Activating Token Index: 282

Text #7

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6171. Min Act: -0.1700

Data Index: 8783709 (Open Web Text)

Max Activating Token Index: 869

Text #8

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6257. Min Act: -0.1700

Data Index: 2443455 (Open Web Text)

Max Activating Token Index: 1000

Text #9

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6344. Min Act: -0.1700

Data Index: 1889566 (Open Web Text)

Max Activating Token Index: 734

Text #10

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6150. Min Act: -0.1700

Data Index: 70739 (Open Web Text)

Max Activating Token Index: 881

Text #11

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6317. Min Act: -0.1700

Data Index: 336205 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6190. Min Act: -0.1700

Data Index: 3418630 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6125. Min Act: -0.1700

Data Index: 2443458 (Open Web Text)

Max Activating Token Index: 251

Text #14

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6087. Min Act: -0.1700

Data Index: 8688137 (Open Web Text)

Max Activating Token Index: 894

Text #15

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6172. Min Act: -0.1700

Data Index: 5651627 (Open Web Text)

Max Activating Token Index: 218

Text #16

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.6065. Min Act: -0.1700

Data Index: 2174820 (Open Web Text)

Max Activating Token Index: 398

Text #17

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.5919. Min Act: -0.1700

Data Index: 1031437 (Open Web Text)

Max Activating Token Index: 450

Text #18

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.5895. Min Act: -0.1700

Data Index: 2018477 (Open Web Text)

Max Activating Token Index: 102

Text #19

Max Range: 4.1596. Min Range: -4.1596

Max Act: 3.5893. Min Act: -0.1700

Data Index: 7650378 (Open Web Text)

Max Activating Token Index: 138