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

Dataset: Open Web Text

Neuron 2054 in Layer 2

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: 4.4085. Min Range: -4.4085

Max Act: 4.4085. Min Act: -0.1700

Data Index: 5763187 (Open Web Text)

Max Activating Token Index: 948

Text #1

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.3383. Min Act: -0.1700

Data Index: 7681792 (Open Web Text)

Max Activating Token Index: 363

Text #2

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.1679. Min Act: -0.1700

Data Index: 6306131 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.1277. Min Act: -0.1700

Data Index: 3456782 (Open Web Text)

Max Activating Token Index: 458

Text #4

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.1265. Min Act: -0.1700

Data Index: 5272732 (Open Web Text)

Max Activating Token Index: 743

Text #5

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.1316. Min Act: -0.1700

Data Index: 5697750 (Open Web Text)

Max Activating Token Index: 838

Text #6

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0905. Min Act: -0.1700

Data Index: 1135372 (Open Web Text)

Max Activating Token Index: 478

Text #7

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.1037. Min Act: -0.1700

Data Index: 6442730 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.1235. Min Act: -0.1700

Data Index: 3725702 (Open Web Text)

Max Activating Token Index: 670

Text #9

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.1196. Min Act: -0.1700

Data Index: 1055255 (Open Web Text)

Max Activating Token Index: 553

Text #10

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.1059. Min Act: -0.1700

Data Index: 7643098 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0975. Min Act: -0.1700

Data Index: 8620060 (Open Web Text)

Max Activating Token Index: 470

Text #12

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0978. Min Act: -0.1700

Data Index: 2529045 (Open Web Text)

Max Activating Token Index: 619

Text #13

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0707. Min Act: -0.1700

Data Index: 4715923 (Open Web Text)

Max Activating Token Index: 750

Text #14

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0661. Min Act: -0.1700

Data Index: 7139425 (Open Web Text)

Max Activating Token Index: 499

Text #15

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0633. Min Act: -0.1700

Data Index: 4288928 (Open Web Text)

Max Activating Token Index: 199

Text #16

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0702. Min Act: -0.1700

Data Index: 1756406 (Open Web Text)

Max Activating Token Index: 976

Text #17

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0840. Min Act: -0.1700

Data Index: 564513 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0855. Min Act: -0.1700

Data Index: 4534253 (Open Web Text)

Max Activating Token Index: 509

Text #19

Max Range: 4.4085. Min Range: -4.4085

Max Act: 4.0738. Min Act: -0.1700

Data Index: 195813 (Open Web Text)

Max Activating Token Index: 482