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

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

Neuron 362 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: 0.0185. Min Range: -0.0185

Max Act: 0.0178. Min Act: -0.0002

Data Index: 479412 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1256358 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0181. Min Act: -0.0002

Data Index: 660559 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0002

Data Index: 935727 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0182. Min Act: -0.0002

Data Index: 1328962 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0165. Min Act: -0.0002

Data Index: 370033 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0173. Min Act: -0.0002

Data Index: 687612 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0163. Min Act: -0.0002

Data Index: 674164 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1007485 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0169. Min Act: -0.0002

Data Index: 709652 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1202061 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1328410 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0159. Min Act: -0.0002

Data Index: 807617 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0158. Min Act: -0.0002

Data Index: 251163 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0158. Min Act: -0.0002

Data Index: 284754 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0153. Min Act: -0.0002

Data Index: 168141 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0149. Min Act: -0.0002

Data Index: 53590 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0153. Min Act: -0.0002

Data Index: 971844 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0145. Min Act: -0.0002

Data Index: 115455 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0148. Min Act: -0.0002

Data Index: 405386 (C4 (Web Text))

Max Activating Token Index: 208