Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2158 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1549. Min Act: -0.0001

Data Index: 324067 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1221. Min Act: -0.0002

Data Index: 857418 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1206. Min Act: -0.0002

Data Index: 78024 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1232. Min Act: -0.0002

Data Index: 610784 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1207. Min Act: -0.0002

Data Index: 49311 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1174. Min Act: -0.0001

Data Index: 168381 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1188. Min Act: -0.0002

Data Index: 342883 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1343. Min Act: -0.0002

Data Index: 657573 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1149. Min Act: -0.0002

Data Index: 803899 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1205. Min Act: -0.0002

Data Index: 363042 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1320. Min Act: -0.0001

Data Index: 379069 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1236. Min Act: -0.0001

Data Index: 834677 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1163566 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1171. Min Act: -0.0001

Data Index: 163992 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1165. Min Act: -0.0002

Data Index: 631680 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1115. Min Act: -0.0002

Data Index: 395349 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1130. Min Act: -0.0002

Data Index: 1297721 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1072425 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1214. Min Act: -0.0002

Data Index: 718708 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.1549. Min Range: -0.1549

Max Act: 0.1111. Min Act: -0.0001

Data Index: 50430 (C4 (Web Text))

Max Activating Token Index: 103