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

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

Neuron 1492 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1839. Min Range: -1.1839

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1115372 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 1.1839. Min Range: -1.1839

Max Act: 1.0509. Min Act: -0.0000

Data Index: 722748 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 1.1839. Min Range: -1.1839

Max Act: 1.0209. Min Act: -0.0000

Data Index: 499040 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.9294. Min Act: -0.0000

Data Index: 928431 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.9868. Min Act: -0.0000

Data Index: 226425 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1329774 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1050985 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1049842 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.9153. Min Act: -0.0000

Data Index: 390771 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.8299. Min Act: -0.0000

Data Index: 193979 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1130352 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.8668. Min Act: -0.0000

Data Index: 767483 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.8226. Min Act: -0.0000

Data Index: 79619 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1229030 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.7994. Min Act: -0.0000

Data Index: 444759 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.7758. Min Act: -0.0000

Data Index: 449922 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.7967. Min Act: -0.0000

Data Index: 934664 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1103265 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1301433 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.1839. Min Range: -1.1839

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1121181 (C4 (Web Text))

Max Activating Token Index: 589