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

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

Neuron 3809 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1473. Min Act: -0.0000

Data Index: 288807 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1389. Min Act: -0.0000

Data Index: 803546 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1156458 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1269. Min Act: -0.0000

Data Index: 682358 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1406. Min Act: -0.0000

Data Index: 665182 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1178. Min Act: -0.0000

Data Index: 69923 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1023015 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1169. Min Act: -0.0000

Data Index: 59582 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1202. Min Act: -0.0000

Data Index: 355717 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1235. Min Act: -0.0000

Data Index: 184085 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1162. Min Act: -0.0000

Data Index: 209914 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1135. Min Act: -0.0001

Data Index: 129377 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1144. Min Act: -0.0001

Data Index: 278723 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1221977 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1186. Min Act: -0.0001

Data Index: 28777 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1084. Min Act: -0.0000

Data Index: 783370 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1218143 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1154. Min Act: -0.0000

Data Index: 447251 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1141. Min Act: -0.0001

Data Index: 210619 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1164. Min Act: -0.0001

Data Index: 967110 (C4 (Web Text))

Max Activating Token Index: 243