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

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

Neuron 2313 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.9351. Min Act: -0.0000

Data Index: 388396 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.6886. Min Act: -0.0000

Data Index: 154482 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.4749. Min Act: -0.0000

Data Index: 1010078 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.6379. Min Act: -0.0000

Data Index: 167049 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.3686. Min Act: -0.0000

Data Index: 114391 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.0947. Min Act: -0.0000

Data Index: 1186550 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.2205. Min Act: -0.0000

Data Index: 939758 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.1682. Min Act: -0.0000

Data Index: 1147154 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.3345. Min Act: -0.0000

Data Index: 1216179 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.2712. Min Act: -0.0000

Data Index: 508498 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.8540. Min Act: -0.0000

Data Index: 464013 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.9832. Min Act: -0.0000

Data Index: 1061209 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 4.9351. Min Range: -4.9351

Max Act: 4.1345. Min Act: -0.0000

Data Index: 225749 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.9454. Min Act: -0.0000

Data Index: 215779 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.9633. Min Act: -0.0000

Data Index: 173792 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.9208. Min Act: -0.0000

Data Index: 551457 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.9059. Min Act: -0.0000

Data Index: 306450 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.7189. Min Act: -0.0000

Data Index: 888009 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.7297. Min Act: -0.0000

Data Index: 179637 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 4.9351. Min Range: -4.9351

Max Act: 3.9049. Min Act: -0.0000

Data Index: 679927 (C4 (Web Text))

Max Activating Token Index: 566