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

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

Neuron 1918 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: 1.6883. Min Range: -1.6883

Max Act: 1.6883. Min Act: -0.0000

Data Index: 89283 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 1.6883. Min Range: -1.6883

Max Act: 1.3323. Min Act: -0.0000

Data Index: 1037834 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.9187. Min Act: -0.0000

Data Index: 494831 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.9802. Min Act: -0.0000

Data Index: 378489 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1188158 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.8930. Min Act: -0.0000

Data Index: 89356 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.8507. Min Act: -0.0000

Data Index: 533159 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.7757. Min Act: -0.0000

Data Index: 469153 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.7885. Min Act: -0.0000

Data Index: 588968 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1277461 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1164793 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1238722 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.7702. Min Act: -0.0000

Data Index: 318564 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.7349. Min Act: -0.0000

Data Index: 461281 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.7313. Min Act: 0.0000

Data Index: 710809 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.8174. Min Act: -0.0000

Data Index: 70664 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.7698. Min Act: -0.0000

Data Index: 644430 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1305732 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.7090. Min Act: -0.0000

Data Index: 975379 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.6883. Min Range: -1.6883

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1087898 (C4 (Web Text))

Max Activating Token Index: 803