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

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

Neuron 2232 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.9033. Min Act: -0.0001

Data Index: 658725 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.9198. Min Act: -0.0001

Data Index: 1193043 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.9432. Min Act: -0.0001

Data Index: 1133121 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8679. Min Act: -0.0001

Data Index: 437388 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.9260. Min Act: -0.0001

Data Index: 52207 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8705. Min Act: -0.0001

Data Index: 1032158 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.9420. Min Act: -0.0001

Data Index: 932716 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8879. Min Act: -0.0001

Data Index: 101181 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.9021. Min Act: -0.0001

Data Index: 854926 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8023. Min Act: -0.0001

Data Index: 1111990 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8375. Min Act: -0.0001

Data Index: 419643 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.9262. Min Act: -0.0001

Data Index: 395528 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8299. Min Act: -0.0001

Data Index: 430994 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8132. Min Act: -0.0001

Data Index: 603661 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8254. Min Act: -0.0001

Data Index: 254450 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8615. Min Act: -0.0001

Data Index: 734435 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7836. Min Act: -0.0001

Data Index: 1008730 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.7806. Min Act: -0.0001

Data Index: 220183 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8034. Min Act: -0.0001

Data Index: 711119 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.9432. Min Range: -0.9432

Max Act: 0.8697. Min Act: -0.0001

Data Index: 991258 (C4 (Web Text))

Max Activating Token Index: 744