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

Dataset: The Pile

Neuron 1730 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1083083 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3813. Min Act: -0.0000

Data Index: 650260 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4843. Min Act: -0.0000

Data Index: 937997 (The Pile)

Max Activating Token Index: 384

Text #3

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.5090. Min Act: -0.0000

Data Index: 335137 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4470. Min Act: -0.0000

Data Index: 439734 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3848. Min Act: -0.0000

Data Index: 940165 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.4476. Min Act: -0.0000

Data Index: 632993 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1459257 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3625. Min Act: 0.0000

Data Index: 322749 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3384. Min Act: -0.0000

Data Index: 412811 (The Pile)

Max Activating Token Index: 887

Text #10

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.2820. Min Act: -0.0000

Data Index: 220104 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3204. Min Act: -0.0000

Data Index: 505049 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1453610 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1611001 (The Pile)

Max Activating Token Index: 229

Text #14

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.2175. Min Act: -0.0000

Data Index: 532550 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.2807. Min Act: 0.0000

Data Index: 1998771 (The Pile)

Max Activating Token Index: 598

Text #16

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.3039. Min Act: -0.0000

Data Index: 386407 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.2371. Min Act: -0.0000

Data Index: 226178 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.2308. Min Act: -0.0000

Data Index: 722167 (The Pile)

Max Activating Token Index: 89

Text #19

Max Range: 0.6069. Min Range: -0.6069

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1485989 (The Pile)

Max Activating Token Index: 620