Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4162 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0124. Min Range: -1.0124

Max Act: 1.0124. Min Act: -0.0002

Data Index: 1255293 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.9042. Min Act: -0.0002

Data Index: 956654 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8232. Min Act: -0.0002

Data Index: 89595 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8305. Min Act: -0.0002

Data Index: 260141 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7178. Min Act: -0.0002

Data Index: 155750 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7159. Min Act: -0.0002

Data Index: 1180589 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.8056. Min Act: -0.0002

Data Index: 1358415 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7753. Min Act: -0.0002

Data Index: 1435165 (Python Code)

Max Activating Token Index: 198

Text #8

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7476. Min Act: -0.0002

Data Index: 1273435 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7374. Min Act: -0.0002

Data Index: 1329821 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7382. Min Act: -0.0002

Data Index: 1004696 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.6978. Min Act: -0.0002

Data Index: 912656 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7136. Min Act: -0.0002

Data Index: 1061214 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7623. Min Act: -0.0002

Data Index: 1174169 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7308. Min Act: -0.0002

Data Index: 658044 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7481. Min Act: -0.0002

Data Index: 1418726 (Python Code)

Max Activating Token Index: 916

Text #16

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7292. Min Act: -0.0002

Data Index: 1335889 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.7452. Min Act: -0.0002

Data Index: 1545359 (Python Code)

Max Activating Token Index: 214

Text #18

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.6891. Min Act: -0.0002

Data Index: 365184 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 1.0124. Min Range: -1.0124

Max Act: 0.6526. Min Act: -0.0002

Data Index: 778061 (C4 (Web Text))

Max Activating Token Index: 600