Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2879 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.9294. Min Act: -0.0001

Data Index: 786528 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.7347. Min Act: -0.0001

Data Index: 1255858 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.9216. Min Act: -0.0001

Data Index: 985322 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.7275. Min Act: -0.0001

Data Index: 582098 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.6910. Min Act: -0.0001

Data Index: 1231204 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.6494. Min Act: -0.0001

Data Index: 75039 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.6432. Min Act: -0.0001

Data Index: 887829 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.5713. Min Act: -0.0001

Data Index: 1158940 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.4967. Min Act: -0.0001

Data Index: 1348803 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.4181. Min Act: -0.0001

Data Index: 13377 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.3483. Min Act: -0.0001

Data Index: 890706 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.4696. Min Act: -0.0001

Data Index: 969234 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.3769. Min Act: -0.0001

Data Index: 617118 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.3294. Min Act: -0.0001

Data Index: 421903 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.3679. Min Act: -0.0001

Data Index: 1174764 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.3537. Min Act: -0.0001

Data Index: 590345 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.3519. Min Act: -0.0001

Data Index: 1208629 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.3112. Min Act: -0.0001

Data Index: 219511 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.2812. Min Act: -0.0001

Data Index: 995463 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 1.9294. Min Range: -1.9294

Max Act: 1.2855. Min Act: -0.0001

Data Index: 200203 (C4 (Web Text))

Max Activating Token Index: 1018