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

Dataset: Open Web Text

Neuron 775 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: 4.5085. Min Range: -4.5085

Max Act: 4.5085. Min Act: -0.1700

Data Index: 4361333 (Open Web Text)

Max Activating Token Index: 926

Text #1

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4965. Min Act: -0.1700

Data Index: 3223985 (Open Web Text)

Max Activating Token Index: 134

Text #2

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4277. Min Act: -0.1700

Data Index: 2913477 (Open Web Text)

Max Activating Token Index: 608

Text #3

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4696. Min Act: -0.1700

Data Index: 6033563 (Open Web Text)

Max Activating Token Index: 260

Text #4

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4583. Min Act: -0.1700

Data Index: 1683718 (Open Web Text)

Max Activating Token Index: 874

Text #5

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4402. Min Act: -0.1700

Data Index: 843806 (Open Web Text)

Max Activating Token Index: 719

Text #6

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4917. Min Act: -0.1700

Data Index: 6192209 (Open Web Text)

Max Activating Token Index: 109

Text #7

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4175. Min Act: -0.1700

Data Index: 8437616 (Open Web Text)

Max Activating Token Index: 621

Text #8

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4304. Min Act: -0.1700

Data Index: 6344772 (Open Web Text)

Max Activating Token Index: 543

Text #9

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4090. Min Act: -0.1700

Data Index: 8737143 (Open Web Text)

Max Activating Token Index: 257

Text #10

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.3834. Min Act: -0.1700

Data Index: 8560695 (Open Web Text)

Max Activating Token Index: 1016

Text #11

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4254. Min Act: -0.1700

Data Index: 1609265 (Open Web Text)

Max Activating Token Index: 564

Text #12

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4278. Min Act: -0.1700

Data Index: 1224894 (Open Web Text)

Max Activating Token Index: 978

Text #13

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.3913. Min Act: -0.1700

Data Index: 5749517 (Open Web Text)

Max Activating Token Index: 577

Text #14

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4563. Min Act: -0.1700

Data Index: 7379538 (Open Web Text)

Max Activating Token Index: 312

Text #15

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4229. Min Act: -0.1700

Data Index: 6381024 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.4345. Min Act: -0.1700

Data Index: 1090685 (Open Web Text)

Max Activating Token Index: 782

Text #17

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.3758. Min Act: -0.1700

Data Index: 3221357 (Open Web Text)

Max Activating Token Index: 122

Text #18

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.3953. Min Act: -0.1700

Data Index: 1038345 (Open Web Text)

Max Activating Token Index: 400

Text #19

Max Range: 4.5085. Min Range: -4.5085

Max Act: 4.3902. Min Act: -0.1700

Data Index: 6338348 (Open Web Text)

Max Activating Token Index: 301