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

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

Neuron 449 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1129925 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1123749 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1565. Min Act: -0.0000

Data Index: 169157 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1272. Min Act: -0.0000

Data Index: 32077 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1346. Min Act: -0.0000

Data Index: 819106 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1232. Min Act: -0.0000

Data Index: 735082 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1278897 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1273. Min Act: -0.0000

Data Index: 603851 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1232. Min Act: -0.0000

Data Index: 662854 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1234. Min Act: -0.0000

Data Index: 699215 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1208. Min Act: -0.0000

Data Index: 595148 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1236. Min Act: -0.0000

Data Index: 225075 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1189. Min Act: -0.0000

Data Index: 407583 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1314457 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1164. Min Act: -0.0000

Data Index: 444915 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1201. Min Act: -0.0000

Data Index: 418259 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1111965 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1318443 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1071. Min Act: -0.0000

Data Index: 304766 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.1690. Min Range: -0.1690

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1291393 (C4 (Web Text))

Max Activating Token Index: 596