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

Dataset: Open Web Text

Neuron 1330 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: 5.4853. Min Range: -5.4853

Max Act: 5.4853. Min Act: -0.1700

Data Index: 4558769 (Open Web Text)

Max Activating Token Index: 406

Text #1

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.4439. Min Act: -0.1700

Data Index: 4204083 (Open Web Text)

Max Activating Token Index: 552

Text #2

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.4627. Min Act: -0.1700

Data Index: 1608163 (Open Web Text)

Max Activating Token Index: 553

Text #3

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3945. Min Act: -0.1700

Data Index: 7472825 (Open Web Text)

Max Activating Token Index: 722

Text #4

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.4017. Min Act: -0.1700

Data Index: 7827683 (Open Web Text)

Max Activating Token Index: 295

Text #5

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3896. Min Act: -0.1700

Data Index: 5014465 (Open Web Text)

Max Activating Token Index: 761

Text #6

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3549. Min Act: -0.1700

Data Index: 2991094 (Open Web Text)

Max Activating Token Index: 364

Text #7

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3694. Min Act: -0.1700

Data Index: 5210161 (Open Web Text)

Max Activating Token Index: 580

Text #8

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3486. Min Act: -0.1700

Data Index: 1981083 (Open Web Text)

Max Activating Token Index: 468

Text #9

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3351. Min Act: -0.1700

Data Index: 1624343 (Open Web Text)

Max Activating Token Index: 227

Text #10

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3418. Min Act: -0.1700

Data Index: 1520199 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3529. Min Act: -0.1700

Data Index: 7275295 (Open Web Text)

Max Activating Token Index: 347

Text #12

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3278. Min Act: -0.1700

Data Index: 1537909 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3266. Min Act: -0.1700

Data Index: 419619 (Open Web Text)

Max Activating Token Index: 472

Text #14

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3235. Min Act: -0.1700

Data Index: 49600 (Open Web Text)

Max Activating Token Index: 383

Text #15

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3344. Min Act: -0.1700

Data Index: 6095220 (Open Web Text)

Max Activating Token Index: 498

Text #16

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3263. Min Act: -0.1700

Data Index: 7188088 (Open Web Text)

Max Activating Token Index: 637

Text #17

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3146. Min Act: -0.1700

Data Index: 7219996 (Open Web Text)

Max Activating Token Index: 199

Text #18

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3230. Min Act: -0.1700

Data Index: 7272837 (Open Web Text)

Max Activating Token Index: 231

Text #19

Max Range: 5.4853. Min Range: -5.4853

Max Act: 5.3325. Min Act: -0.1700

Data Index: 2108254 (Open Web Text)

Max Activating Token Index: 659