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

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

Neuron 2995 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.4296. Min Act: -0.0002

Data Index: 9290 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3379. Min Act: -0.0002

Data Index: 1173404 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3038. Min Act: -0.0002

Data Index: 109553 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3022. Min Act: -0.0003

Data Index: 863093 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3069. Min Act: -0.0003

Data Index: 889772 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2946. Min Act: -0.0002

Data Index: 790335 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2984. Min Act: -0.0003

Data Index: 415193 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2863. Min Act: -0.0003

Data Index: 162244 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3059. Min Act: -0.0002

Data Index: 669773 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.3029. Min Act: -0.0003

Data Index: 779740 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2920. Min Act: -0.0002

Data Index: 652896 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2858. Min Act: -0.0002

Data Index: 1082285 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2848. Min Act: -0.0002

Data Index: 937640 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2749. Min Act: -0.0003

Data Index: 1179146 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2834. Min Act: -0.0002

Data Index: 652056 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2919. Min Act: -0.0002

Data Index: 395256 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2814. Min Act: -0.0003

Data Index: 559819 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2819. Min Act: -0.0002

Data Index: 293823 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2804. Min Act: -0.0002

Data Index: 99173 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.4296. Min Range: -0.4296

Max Act: 0.2785. Min Act: -0.0003

Data Index: 640082 (C4 (Web Text))

Max Activating Token Index: 146