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

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

Neuron 1689 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1111898 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1280601 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0169. Min Act: -0.0006

Data Index: 149922 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1051670 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0174. Min Act: -0.0006

Data Index: 580357 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0170. Min Act: -0.0006

Data Index: 485957 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0166. Min Act: -0.0006

Data Index: 3711 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0173. Min Act: -0.0006

Data Index: 428598 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1333019 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0171. Min Act: -0.0006

Data Index: 459250 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1062158 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0163. Min Act: -0.0006

Data Index: 125182 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0162. Min Act: -0.0005

Data Index: 769049 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0170. Min Act: -0.0006

Data Index: 601122 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0158. Min Act: -0.0006

Data Index: 34357 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0167. Min Act: -0.0006

Data Index: 246872 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0160. Min Act: -0.0006

Data Index: 11945 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0160. Min Act: -0.0006

Data Index: 733677 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1188984 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.0267. Min Range: -0.0267

Max Act: 0.0156. Min Act: -0.0006

Data Index: 536518 (C4 (Web Text))

Max Activating Token Index: 743