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

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

Neuron 1566 in Layer 1

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: 0.0254. Min Range: -0.0254

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1605654 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0215. Min Act: -0.0002

Data Index: 433996 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0200. Min Act: -0.0002

Data Index: 197530 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1455958 (Python Code)

Max Activating Token Index: 177

Text #4

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0193. Min Act: -0.0002

Data Index: 856299 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0191. Min Act: -0.0002

Data Index: 414727 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0194. Min Act: -0.0002

Data Index: 276259 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0189. Min Act: -0.0002

Data Index: 997712 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0193. Min Act: -0.0002

Data Index: 46598 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0185. Min Act: -0.0002

Data Index: 644433 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0184. Min Act: -0.0002

Data Index: 551963 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1648241 (Python Code)

Max Activating Token Index: 410

Text #12

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0179. Min Act: -0.0002

Data Index: 680805 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1075702 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0173. Min Act: -0.0003

Data Index: 920767 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1359823 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0172. Min Act: -0.0002

Data Index: 280296 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0165. Min Act: -0.0002

Data Index: 288566 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1482674 (Python Code)

Max Activating Token Index: 419

Text #19

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0162. Min Act: -0.0003

Data Index: 280457 (C4 (Web Text))

Max Activating Token Index: 975