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

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

Neuron 1840 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0273. Min Act: -0.0006

Data Index: 85444 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0192. Min Act: -0.0006

Data Index: 963343 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0192. Min Act: -0.0006

Data Index: 604046 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0188. Min Act: -0.0006

Data Index: 486209 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0183. Min Act: -0.0006

Data Index: 1018327 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1264952 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1008168 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0175. Min Act: -0.0006

Data Index: 294379 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0178. Min Act: -0.0006

Data Index: 1056877 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0167. Min Act: -0.0006

Data Index: 459815 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1036984 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0165. Min Act: -0.0006

Data Index: 162724 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0168. Min Act: -0.0006

Data Index: 359973 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0171. Min Act: -0.0006

Data Index: 362081 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1142149 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1183824 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0160. Min Act: -0.0006

Data Index: 891737 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0160. Min Act: -0.0006

Data Index: 541180 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0168. Min Act: -0.0006

Data Index: 938731 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.0273. Min Range: -0.0273

Max Act: 0.0166. Min Act: -0.0006

Data Index: 929508 (C4 (Web Text))

Max Activating Token Index: 667