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

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

Neuron 31 in Layer 0

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: 0.0185. Min Act: -0.0002

Data Index: 1500234 (Python Code)

Max Activating Token Index: 88

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1357583 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0176. Min Act: -0.0002

Data Index: 806494 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1140535 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0174. Min Act: -0.0002

Data Index: 159537 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1088076 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0172. Min Act: -0.0002

Data Index: 398969 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1355693 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1317049 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0169. Min Act: -0.0002

Data Index: 94691 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0169. Min Act: -0.0002

Data Index: 120454 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0165. Min Act: -0.0002

Data Index: 648214 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1285227 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0164. Min Act: -0.0002

Data Index: 113439 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0164. Min Act: -0.0002

Data Index: 449705 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1005285 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0162. Min Act: -0.0002

Data Index: 211853 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0161. Min Act: -0.0002

Data Index: 190864 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0160. Min Act: -0.0002

Data Index: 499027 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0159. Min Act: -0.0002

Data Index: 454342 (C4 (Web Text))

Max Activating Token Index: 38