Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3357 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.7810. Min Act: -0.0000

Data Index: 376933 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.6475. Min Act: -0.0000

Data Index: 91614 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.5834. Min Act: -0.0000

Data Index: 1083035 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.5355. Min Act: -0.0000

Data Index: 359 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.4716. Min Act: -0.0000

Data Index: 386108 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.4668. Min Act: -0.0000

Data Index: 827736 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.4694. Min Act: -0.0000

Data Index: 1353575 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.4602. Min Act: -0.0000

Data Index: 1230796 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.5234. Min Act: -0.0000

Data Index: 698620 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.5187. Min Act: -0.0000

Data Index: 184796 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.3943. Min Act: -0.0000

Data Index: 167075 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.3883. Min Act: -0.0000

Data Index: 250524 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.3671. Min Act: -0.0000

Data Index: 1128951 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.2779. Min Act: -0.0000

Data Index: 449816 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.3447. Min Act: -0.0000

Data Index: 351624 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.3432. Min Act: -0.0000

Data Index: 660701 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.3455. Min Act: -0.0000

Data Index: 867035 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.3406. Min Act: -0.0000

Data Index: 243575 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.3184. Min Act: -0.0000

Data Index: 267588 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 1.7810. Min Range: -1.7810

Max Act: 1.3256. Min Act: -0.0000

Data Index: 916453 (C4 (Web Text))

Max Activating Token Index: 382