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

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

Neuron 1053 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: 4.3488. Min Range: -4.3488

Max Act: 4.3488. Min Act: -0.0000

Data Index: 1029547 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.3351. Min Act: -0.0000

Data Index: 174210 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 4.3488. Min Range: -4.3488

Max Act: 4.1654. Min Act: -0.0000

Data Index: 1264985 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.7952. Min Act: -0.0000

Data Index: 963259 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.4612. Min Act: -0.0000

Data Index: 486367 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.7082. Min Act: -0.0000

Data Index: 837635 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.4851. Min Act: -0.0000

Data Index: 146608 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.4640. Min Act: -0.0000

Data Index: 653097 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.2572. Min Act: -0.0000

Data Index: 511013 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.3553. Min Act: -0.0000

Data Index: 1023804 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.3258. Min Act: -0.0000

Data Index: 1034041 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.3247. Min Act: -0.0000

Data Index: 1043395 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.1398. Min Act: -0.0000

Data Index: 333848 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 4.3488. Min Range: -4.3488

Max Act: 2.9582. Min Act: -0.0000

Data Index: 1216729 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.1072. Min Act: -0.0000

Data Index: 67256 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.2375. Min Act: -0.0000

Data Index: 880960 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.0446. Min Act: -0.0000

Data Index: 832251 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 4.3488. Min Range: -4.3488

Max Act: 3.0250. Min Act: -0.0000

Data Index: 1080251 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 4.3488. Min Range: -4.3488

Max Act: 2.8128. Min Act: -0.0000

Data Index: 462850 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 4.3488. Min Range: -4.3488

Max Act: 2.6790. Min Act: -0.0000

Data Index: 82945 (C4 (Web Text))

Max Activating Token Index: 97