Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 601 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0214. Min Act: -0.0007

Data Index: 1267959 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0209. Min Act: -0.0006

Data Index: 1108378 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0208. Min Act: -0.0006

Data Index: 647811 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0200. Min Act: -0.0006

Data Index: 801742 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0192. Min Act: -0.0006

Data Index: 249360 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0192. Min Act: -0.0006

Data Index: 769270 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0191. Min Act: -0.0006

Data Index: 509859 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1184678 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0180. Min Act: -0.0006

Data Index: 381463 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0178. Min Act: -0.0006

Data Index: 838697 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1351775 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0182. Min Act: -0.0006

Data Index: 420639 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0172. Min Act: -0.0006

Data Index: 379477 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0172. Min Act: -0.0006

Data Index: 963317 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0176. Min Act: -0.0006

Data Index: 261629 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0175. Min Act: -0.0006

Data Index: 233441 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0171. Min Act: -0.0006

Data Index: 549483 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1125022 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0175. Min Act: -0.0006

Data Index: 295831 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0178. Min Act: -0.0006

Data Index: 105416 (C4 (Web Text))

Max Activating Token Index: 137