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

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

Neuron 896 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2549. Min Act: -0.0002

Data Index: 429842 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2397. Min Act: -0.0002

Data Index: 1318907 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2404. Min Act: 0.0000

Data Index: 458028 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2324. Min Act: -0.0001

Data Index: 804482 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1163756 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2168. Min Act: -0.0002

Data Index: 1093497 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2259. Min Act: -0.0001

Data Index: 695357 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1347365 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2174. Min Act: -0.0001

Data Index: 647623 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2271. Min Act: -0.0002

Data Index: 536912 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2168. Min Act: -0.0001

Data Index: 380596 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2233. Min Act: -0.0002

Data Index: 330678 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2145. Min Act: -0.0001

Data Index: 766970 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2208. Min Act: -0.0002

Data Index: 426547 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2141. Min Act: -0.0002

Data Index: 513846 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2157. Min Act: -0.0002

Data Index: 122942 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2182. Min Act: -0.0002

Data Index: 514137 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2214. Min Act: -0.0002

Data Index: 406431 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2170. Min Act: -0.0002

Data Index: 1169925 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.2549. Min Range: -0.2549

Max Act: 0.2230. Min Act: -0.0002

Data Index: 205927 (C4 (Web Text))

Max Activating Token Index: 518