Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1510 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2880. Min Act: -0.0000

Data Index: 474997 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2783. Min Act: -0.0000

Data Index: 562125 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2608. Min Act: -0.0000

Data Index: 336847 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1891910 (The Pile)

Max Activating Token Index: 968

Text #4

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.3007. Min Act: -0.0000

Data Index: 183457 (The Pile)

Max Activating Token Index: 93

Text #5

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2539. Min Act: -0.0000

Data Index: 763972 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2681. Min Act: -0.0000

Data Index: 844621 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1984565 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2588. Min Act: -0.0000

Data Index: 7646 (The Pile)

Max Activating Token Index: 344

Text #9

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1189166 (The Pile)

Max Activating Token Index: 760

Text #10

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1605149 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2376. Min Act: -0.0000

Data Index: 606152 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2629. Min Act: -0.0000

Data Index: 784675 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1316094 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1217953 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2401. Min Act: -0.0000

Data Index: 674629 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2350. Min Act: -0.0000

Data Index: 871002 (The Pile)

Max Activating Token Index: 747

Text #17

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1845256 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2097. Min Act: -0.0000

Data Index: 1364323 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 0.3007. Min Range: -0.3007

Max Act: 0.2108. Min Act: -0.0000

Data Index: 631891 (The Pile)

Max Activating Token Index: 628