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

Dataset: Open Web Text

Neuron 763 in Layer 1

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: 2.0499. Min Range: -2.0499

Max Act: 2.0499. Min Act: -0.1700

Data Index: 500316 (Open Web Text)

Max Activating Token Index: 204

Text #1

Max Range: 2.0499. Min Range: -2.0499

Max Act: 2.0355. Min Act: -0.1700

Data Index: 7524742 (Open Web Text)

Max Activating Token Index: 139

Text #2

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9396. Min Act: -0.1700

Data Index: 3580744 (Open Web Text)

Max Activating Token Index: 51

Text #3

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9500. Min Act: -0.1700

Data Index: 4649843 (Open Web Text)

Max Activating Token Index: 651

Text #4

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9388. Min Act: -0.1700

Data Index: 8217673 (Open Web Text)

Max Activating Token Index: 102

Text #5

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9239. Min Act: -0.1700

Data Index: 3620421 (Open Web Text)

Max Activating Token Index: 139

Text #6

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9246. Min Act: -0.1700

Data Index: 1420270 (Open Web Text)

Max Activating Token Index: 675

Text #7

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9199. Min Act: -0.1700

Data Index: 2628096 (Open Web Text)

Max Activating Token Index: 659

Text #8

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9264. Min Act: -0.1700

Data Index: 222402 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9296. Min Act: -0.1700

Data Index: 2017072 (Open Web Text)

Max Activating Token Index: 338

Text #10

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9182. Min Act: -0.1700

Data Index: 1090079 (Open Web Text)

Max Activating Token Index: 899

Text #11

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9125. Min Act: -0.1700

Data Index: 2189943 (Open Web Text)

Max Activating Token Index: 904

Text #12

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9055. Min Act: -0.1700

Data Index: 6827708 (Open Web Text)

Max Activating Token Index: 186

Text #13

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9155. Min Act: -0.1700

Data Index: 8692014 (Open Web Text)

Max Activating Token Index: 188

Text #14

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9126. Min Act: -0.1697

Data Index: 8682984 (Open Web Text)

Max Activating Token Index: 573

Text #15

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9161. Min Act: -0.1700

Data Index: 6188207 (Open Web Text)

Max Activating Token Index: 73

Text #16

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9141. Min Act: -0.1700

Data Index: 8682983 (Open Web Text)

Max Activating Token Index: 529

Text #17

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9016. Min Act: -0.1700

Data Index: 3971409 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9190. Min Act: -0.1700

Data Index: 7707945 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 2.0499. Min Range: -2.0499

Max Act: 1.9193. Min Act: -0.1700

Data Index: 3816274 (Open Web Text)

Max Activating Token Index: 303