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

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

Neuron 3478 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1334. Min Act: -0.0001

Data Index: 1087178 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1029. Min Act: -0.0001

Data Index: 177250 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0910. Min Act: -0.0000

Data Index: 648777 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1355429 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0929. Min Act: -0.0000

Data Index: 334694 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0978. Min Act: -0.0000

Data Index: 66906 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.1032. Min Act: -0.0000

Data Index: 75480 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0860. Min Act: -0.0000

Data Index: 100775 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0821. Min Act: -0.0000

Data Index: 898031 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1205260 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0852. Min Act: -0.0000

Data Index: 805218 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0960. Min Act: -0.0000

Data Index: 843970 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0860. Min Act: -0.0000

Data Index: 49551 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0897. Min Act: -0.0000

Data Index: 677476 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0860. Min Act: -0.0000

Data Index: 990612 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0801. Min Act: -0.0000

Data Index: 222249 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0929. Min Act: -0.0000

Data Index: 157878 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0815. Min Act: -0.0000

Data Index: 417351 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1088545 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.1334. Min Range: -0.1334

Max Act: 0.0826. Min Act: -0.0000

Data Index: 313269 (C4 (Web Text))

Max Activating Token Index: 45