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

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

Neuron 3069 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.3337. Min Act: -0.0000

Data Index: 1332105 (C4 (Web Text))

Max Activating Token Index: 942

Text #1

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2936. Min Act: -0.0000

Data Index: 476172 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2574. Min Act: -0.0000

Data Index: 448381 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2859. Min Act: -0.0000

Data Index: 1123868 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2673. Min Act: -0.0000

Data Index: 956120 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2579. Min Act: -0.0000

Data Index: 760506 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2733. Min Act: -0.0000

Data Index: 31766 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1147369 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2521. Min Act: -0.0000

Data Index: 542191 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2380. Min Act: -0.0001

Data Index: 195471 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2458. Min Act: -0.0000

Data Index: 128775 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2464. Min Act: -0.0000

Data Index: 83211 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2441. Min Act: -0.0000

Data Index: 40980 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2438. Min Act: -0.0000

Data Index: 771738 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2455. Min Act: -0.0000

Data Index: 990162 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1024536 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2327. Min Act: -0.0001

Data Index: 636195 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2213. Min Act: -0.0000

Data Index: 303528 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2296. Min Act: -0.0001

Data Index: 765793 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.3337. Min Range: -0.3337

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1019549 (C4 (Web Text))

Max Activating Token Index: 75