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

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

Neuron 400 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: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0006

Data Index: 280615 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0175. Min Act: -0.0006

Data Index: 403768 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0172. Min Act: -0.0006

Data Index: 746864 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1306630 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0170. Min Act: -0.0006

Data Index: 1279391 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0168. Min Act: -0.0006

Data Index: 31514 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0167. Min Act: -0.0006

Data Index: 116007 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0006

Data Index: 583958 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1221558 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0006

Data Index: 896066 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0162. Min Act: -0.0006

Data Index: 175099 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0165. Min Act: -0.0006

Data Index: 832534 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0006

Data Index: 447198 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0160. Min Act: -0.0006

Data Index: 69889 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0164. Min Act: -0.0007

Data Index: 68016 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1177024 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0160. Min Act: -0.0006

Data Index: 60329 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0163. Min Act: -0.0006

Data Index: 228101 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0006

Data Index: 578358 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0162. Min Act: -0.0006

Data Index: 651236 (C4 (Web Text))

Max Activating Token Index: 635