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

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

Neuron 4070 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1484. Min Act: -0.0000

Data Index: 181225 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1351. Min Act: -0.0000

Data Index: 287193 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1401. Min Act: -0.0000

Data Index: 958305 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1289. Min Act: -0.0000

Data Index: 910362 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1284. Min Act: -0.0000

Data Index: 984037 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1247. Min Act: -0.0000

Data Index: 644562 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1290. Min Act: -0.0000

Data Index: 434198 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1214. Min Act: -0.0000

Data Index: 243671 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1249. Min Act: -0.0000

Data Index: 418354 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1357. Min Act: -0.0000

Data Index: 952833 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1204. Min Act: -0.0000

Data Index: 871075 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1124322 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1270383 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1123. Min Act: -0.0000

Data Index: 522340 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1164. Min Act: -0.0000

Data Index: 421736 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1311977 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1107. Min Act: -0.0000

Data Index: 801585 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1049651 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1140. Min Act: -0.0000

Data Index: 591140 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.1484. Min Range: -0.1484

Max Act: 0.1077. Min Act: -0.0000

Data Index: 1346183 (C4 (Web Text))

Max Activating Token Index: 221