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

Dataset: The Pile

Neuron 647 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4456. Min Act: -0.0000

Data Index: 6502 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.4470. Min Act: -0.0000

Data Index: 634467 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1811965 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3870. Min Act: -0.0000

Data Index: 241600 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3176. Min Act: -0.0000

Data Index: 46638 (The Pile)

Max Activating Token Index: 414

Text #5

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2429. Min Act: -0.0000

Data Index: 133222 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3143. Min Act: -0.0000

Data Index: 39184 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1230821 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2784. Min Act: -0.0000

Data Index: 852396 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1406138 (The Pile)

Max Activating Token Index: 812

Text #10

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1249143 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2938. Min Act: -0.0000

Data Index: 1775761 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2540. Min Act: -0.0000

Data Index: 688572 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.3092. Min Act: -0.0000

Data Index: 249629 (The Pile)

Max Activating Token Index: 619

Text #14

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2517. Min Act: -0.0000

Data Index: 1342567 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2644. Min Act: -0.0000

Data Index: 787959 (The Pile)

Max Activating Token Index: 447

Text #16

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2482. Min Act: -0.0000

Data Index: 93906 (The Pile)

Max Activating Token Index: 707

Text #17

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2684. Min Act: -0.0000

Data Index: 434031 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2525. Min Act: -0.0000

Data Index: 191404 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.4470. Min Range: -0.4470

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1642700 (The Pile)

Max Activating Token Index: 1013