Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 409 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1316102 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0157. Min Act: -0.0006

Data Index: 56401 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0155. Min Act: -0.0006

Data Index: 431206 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0150. Min Act: -0.0006

Data Index: 100481 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1184924 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0151. Min Act: -0.0006

Data Index: 58986 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0150. Min Act: -0.0006

Data Index: 373553 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0150. Min Act: -0.0006

Data Index: 442296 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1247859 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0149. Min Act: -0.0006

Data Index: 73171 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0145. Min Act: -0.0006

Data Index: 383477 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0148. Min Act: -0.0006

Data Index: 259180 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0147. Min Act: -0.0006

Data Index: 756419 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0143. Min Act: -0.0007

Data Index: 1141715 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0146. Min Act: -0.0006

Data Index: 811615 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1059350 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0146. Min Act: -0.0006

Data Index: 588537 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0144. Min Act: -0.0006

Data Index: 679645 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0141. Min Act: -0.0006

Data Index: 456012 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0145. Min Act: -0.0006

Data Index: 986096 (C4 (Web Text))

Max Activating Token Index: 418