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

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

Neuron 1643 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3732. Min Act: -0.0000

Data Index: 115695 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1346584 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2979. Min Act: -0.0000

Data Index: 203223 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3087. Min Act: -0.0000

Data Index: 213087 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3224. Min Act: -0.0000

Data Index: 492311 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3233. Min Act: -0.0000

Data Index: 355220 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2861. Min Act: -0.0000

Data Index: 96589 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1147547 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2731. Min Act: -0.0000

Data Index: 171464 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2857. Min Act: -0.0000

Data Index: 658985 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2921. Min Act: -0.0000

Data Index: 106375 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2738. Min Act: -0.0000

Data Index: 673017 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2713. Min Act: -0.0000

Data Index: 185841 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.3017. Min Act: -0.0000

Data Index: 405505 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1114221 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1002291 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2720. Min Act: -0.0000

Data Index: 627587 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2727. Min Act: -0.0000

Data Index: 826046 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2585. Min Act: -0.0000

Data Index: 70663 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.3732. Min Range: -0.3732

Max Act: 0.2783. Min Act: -0.0000

Data Index: 733811 (C4 (Web Text))

Max Activating Token Index: 890