Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3438 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1385. Min Act: -0.0000

Data Index: 536133 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1374. Min Act: -0.0000

Data Index: 426909 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1267. Min Act: -0.0000

Data Index: 262522 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1270. Min Act: -0.0000

Data Index: 933440 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1310. Min Act: -0.0000

Data Index: 671281 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1255. Min Act: -0.0000

Data Index: 664063 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1232. Min Act: -0.0000

Data Index: 96510 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1178. Min Act: -0.0000

Data Index: 511734 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1101582 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1170. Min Act: -0.0000

Data Index: 874526 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1168. Min Act: -0.0000

Data Index: 157605 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1234. Min Act: -0.0000

Data Index: 309089 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1055. Min Act: -0.0000

Data Index: 219389 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1163. Min Act: -0.0000

Data Index: 773796 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1171966 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1118217 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1093. Min Act: -0.0000

Data Index: 193057 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1123. Min Act: -0.0000

Data Index: 180375 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1073774 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1087. Min Act: -0.0000

Data Index: 306353 (C4 (Web Text))

Max Activating Token Index: 817