Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3817 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1304571 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1308. Min Act: -0.0000

Data Index: 820849 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1215466 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1099499 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1117848 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1331. Min Act: -0.0000

Data Index: 956571 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1230875 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1174. Min Act: -0.0000

Data Index: 975222 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1207. Min Act: -0.0000

Data Index: 396906 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1314239 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1194. Min Act: -0.0000

Data Index: 67121 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1144. Min Act: -0.0000

Data Index: 436912 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1178. Min Act: -0.0000

Data Index: 810796 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1008450 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1155. Min Act: -0.0000

Data Index: 550344 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1167. Min Act: -0.0000

Data Index: 689180 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1128. Min Act: -0.0000

Data Index: 304170 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1108. Min Act: -0.0000

Data Index: 499388 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1098941 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.1385. Min Range: -0.1385

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1229036 (C4 (Web Text))

Max Activating Token Index: 331