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

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

Neuron 3460 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1156557 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0194. Min Act: -0.0001

Data Index: 676339 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0189. Min Act: -0.0001

Data Index: 8836 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0180. Min Act: -0.0001

Data Index: 568001 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0001

Data Index: 940297 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1631753 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1381066 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0002

Data Index: 673849 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1560474 (Python Code)

Max Activating Token Index: 479

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1561319 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1625126 (Python Code)

Max Activating Token Index: 38

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0175. Min Act: -0.0001

Data Index: 1554331 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0001

Data Index: 322788 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0173. Min Act: -0.0001

Data Index: 521284 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1463111 (Python Code)

Max Activating Token Index: 281

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1452418 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0001

Data Index: 292743 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0167. Min Act: -0.0001

Data Index: 1590644 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1358828 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0001

Data Index: 582147 (C4 (Web Text))

Max Activating Token Index: 201