Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5678 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1154243 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0185. Min Act: -0.0002

Data Index: 371729 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0179. Min Act: -0.0002

Data Index: 121551 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1214824 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0177. Min Act: -0.0002

Data Index: 351963 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0171. Min Act: -0.0002

Data Index: 247068 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0171. Min Act: -0.0002

Data Index: 621192 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0173. Min Act: -0.0002

Data Index: 396840 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0163. Min Act: -0.0002

Data Index: 170472 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0155. Min Act: -0.0002

Data Index: 57533 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1033588 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0153. Min Act: -0.0002

Data Index: 623285 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0158. Min Act: -0.0002

Data Index: 760626 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0149. Min Act: -0.0002

Data Index: 85923 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0152. Min Act: -0.0002

Data Index: 794641 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1527586 (Python Code)

Max Activating Token Index: 323

Text #16

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1285724 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0150. Min Act: -0.0002

Data Index: 551330 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1127523 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.0202. Min Range: -0.0202

Max Act: 0.0149. Min Act: -0.0002

Data Index: 427978 (C4 (Web Text))

Max Activating Token Index: 964