Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4832 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0002

Data Index: 483518 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0236. Min Act: -0.0002

Data Index: 782231 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1570100 (Python Code)

Max Activating Token Index: 518

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1330995 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0203. Min Act: -0.0002

Data Index: 147045 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1177052 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1116670 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0178. Min Act: -0.0002

Data Index: 993452 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0169. Min Act: -0.0002

Data Index: 422112 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0181. Min Act: -0.0002

Data Index: 940562 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0165. Min Act: -0.0002

Data Index: 540652 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1190103 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0170. Min Act: -0.0002

Data Index: 700581 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0165. Min Act: -0.0002

Data Index: 559563 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0156. Min Act: -0.0002

Data Index: 734866 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0157. Min Act: -0.0002

Data Index: 202359 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0162. Min Act: -0.0002

Data Index: 26301 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0158. Min Act: -0.0002

Data Index: 923250 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0160. Min Act: -0.0002

Data Index: 803488 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0162. Min Act: -0.0002

Data Index: 227775 (C4 (Web Text))

Max Activating Token Index: 315