Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1678 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0209. Min Act: -0.0006

Data Index: 59274 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1284655 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0211. Min Act: -0.0006

Data Index: 542977 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0203. Min Act: -0.0006

Data Index: 1167431 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1049242 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0189. Min Act: -0.0006

Data Index: 281165 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0186. Min Act: -0.0006

Data Index: 478176 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1140763 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1157339 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0189. Min Act: -0.0006

Data Index: 607206 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0188. Min Act: -0.0006

Data Index: 794032 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1141633 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1092332 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0182. Min Act: -0.0006

Data Index: 896900 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0178. Min Act: -0.0006

Data Index: 758035 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0182. Min Act: -0.0006

Data Index: 285256 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0173. Min Act: -0.0006

Data Index: 70158 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0176. Min Act: -0.0006

Data Index: 48205 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0171. Min Act: -0.0006

Data Index: 959362 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0173. Min Act: -0.0006

Data Index: 263036 (C4 (Web Text))

Max Activating Token Index: 1017