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

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

Neuron 782 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.5976. Min Act: -0.0002

Data Index: 767783 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.6364. Min Act: -0.0002

Data Index: 1163994 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.5640. Min Act: -0.0002

Data Index: 574610 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.5525. Min Act: -0.0002

Data Index: 1355910 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.5388. Min Act: -0.0002

Data Index: 822391 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4841. Min Act: -0.0003

Data Index: 702286 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.5089. Min Act: -0.0002

Data Index: 1058046 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.5414. Min Act: -0.0002

Data Index: 740594 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4678. Min Act: -0.0002

Data Index: 586737 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4212. Min Act: -0.0002

Data Index: 1025240 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4188. Min Act: -0.0002

Data Index: 73547 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4540. Min Act: -0.0003

Data Index: 1247021 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4421. Min Act: -0.0002

Data Index: 1117262 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4494. Min Act: -0.0002

Data Index: 1096861 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4043. Min Act: -0.0003

Data Index: 1323513 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4451. Min Act: -0.0002

Data Index: 596170 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4002. Min Act: -0.0002

Data Index: 187315 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4141. Min Act: -0.0002

Data Index: 391767 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.4097. Min Act: -0.0002

Data Index: 1294284 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.6364. Min Range: -1.6364

Max Act: 1.3584. Min Act: -0.0002

Data Index: 881547 (C4 (Web Text))

Max Activating Token Index: 283