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

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

Neuron 831 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1345106 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0212. Min Act: -0.0003

Data Index: 976381 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0176. Min Act: -0.0003

Data Index: 815268 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0183. Min Act: -0.0003

Data Index: 3457 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0174. Min Act: -0.0003

Data Index: 477917 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1427873 (Python Code)

Max Activating Token Index: 473

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1537801 (Python Code)

Max Activating Token Index: 240

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0181. Min Act: -0.0003

Data Index: 1309929 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0171. Min Act: -0.0003

Data Index: 1184257 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0172. Min Act: -0.0003

Data Index: 203905 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1602214 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1470222 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0173. Min Act: -0.0003

Data Index: 9526 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0173. Min Act: -0.0003

Data Index: 95842 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1457787 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1494256 (Python Code)

Max Activating Token Index: 356

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1443877 (Python Code)

Max Activating Token Index: 183

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0158. Min Act: -0.0003

Data Index: 671637 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1451880 (Python Code)

Max Activating Token Index: 480

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0158. Min Act: -0.0003

Data Index: 366051 (C4 (Web Text))

Max Activating Token Index: 489