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

Dataset: Open Web Text

Neuron 1857 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: 3.4472. Min Range: -3.4472

Max Act: 3.4472. Min Act: -0.1700

Data Index: 4474260 (Open Web Text)

Max Activating Token Index: 40

Text #1

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3762. Min Act: -0.1700

Data Index: 6330438 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3005. Min Act: -0.1700

Data Index: 585320 (Open Web Text)

Max Activating Token Index: 74

Text #3

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.3264. Min Act: -0.1700

Data Index: 2339497 (Open Web Text)

Max Activating Token Index: 24

Text #4

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2796. Min Act: -0.1700

Data Index: 3227840 (Open Web Text)

Max Activating Token Index: 24

Text #5

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2310. Min Act: -0.1700

Data Index: 2986724 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2273. Min Act: -0.1700

Data Index: 1287180 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1869. Min Act: -0.1700

Data Index: 2748139 (Open Web Text)

Max Activating Token Index: 195

Text #8

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1864. Min Act: -0.1700

Data Index: 7281295 (Open Web Text)

Max Activating Token Index: 33

Text #9

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2108. Min Act: -0.1700

Data Index: 7195287 (Open Web Text)

Max Activating Token Index: 27

Text #10

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2078. Min Act: -0.1700

Data Index: 8228237 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1842. Min Act: -0.1700

Data Index: 1708896 (Open Web Text)

Max Activating Token Index: 606

Text #12

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.2056. Min Act: -0.1700

Data Index: 4016215 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1549. Min Act: -0.1700

Data Index: 1551552 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1642. Min Act: -0.1700

Data Index: 8778705 (Open Web Text)

Max Activating Token Index: 834

Text #15

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1819. Min Act: -0.1700

Data Index: 2255254 (Open Web Text)

Max Activating Token Index: 740

Text #16

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1508. Min Act: -0.1700

Data Index: 8010091 (Open Web Text)

Max Activating Token Index: 192

Text #17

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1611. Min Act: -0.1700

Data Index: 2986720 (Open Web Text)

Max Activating Token Index: 470

Text #18

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1496. Min Act: -0.1700

Data Index: 3894328 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.4472. Min Range: -3.4472

Max Act: 3.1489. Min Act: -0.1700

Data Index: 1515379 (Open Web Text)

Max Activating Token Index: 93