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

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

Neuron 590 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.9688. Min Act: -0.0000

Data Index: 931259 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.3152. Min Act: -0.0000

Data Index: 1357350 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.3255. Min Act: -0.0000

Data Index: 749416 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.2382. Min Act: -0.0000

Data Index: 456314 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.2267. Min Act: -0.0000

Data Index: 506847 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.2201. Min Act: -0.0000

Data Index: 626539 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.2024. Min Act: -0.0000

Data Index: 507854 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.1902. Min Act: -0.0000

Data Index: 350322 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.1582. Min Act: -0.0000

Data Index: 1348858 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.1397. Min Act: -0.0000

Data Index: 429783 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.1320. Min Act: -0.0000

Data Index: 576353 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.1288. Min Act: -0.0000

Data Index: 1003711 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.1386. Min Act: -0.0000

Data Index: 166215 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.0872. Min Act: -0.0000

Data Index: 854681 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.0953. Min Act: -0.0000

Data Index: 31519 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.0807. Min Act: -0.0000

Data Index: 1053816 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 2.9688. Min Range: -2.9688

Max Act: 1.9765. Min Act: -0.0000

Data Index: 804555 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.3119. Min Act: -0.0000

Data Index: 496933 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 2.9688. Min Range: -2.9688

Max Act: 1.9560. Min Act: -0.0000

Data Index: 863627 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 2.9688. Min Range: -2.9688

Max Act: 2.1913. Min Act: -0.0000

Data Index: 1285397 (C4 (Web Text))

Max Activating Token Index: 145