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

Dataset: The Pile

Neuron 2329 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: 1.2987. Min Range: -1.2987

Max Act: 1.2987. Min Act: -0.0000

Data Index: 76383 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 1.2987. Min Range: -1.2987

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1189301 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.9105. Min Act: -0.0000

Data Index: 990056 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7029. Min Act: -0.0000

Data Index: 954320 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1043386 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1421282 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.8246. Min Act: -0.0000

Data Index: 821417 (The Pile)

Max Activating Token Index: 779

Text #7

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7737. Min Act: -0.0000

Data Index: 1411412 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7204. Min Act: -0.0000

Data Index: 657211 (The Pile)

Max Activating Token Index: 428

Text #9

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7128. Min Act: -0.0000

Data Index: 558096 (The Pile)

Max Activating Token Index: 872

Text #10

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.6160. Min Act: -0.0000

Data Index: 715585 (The Pile)

Max Activating Token Index: 269

Text #11

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1664949 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.7151. Min Act: -0.0000

Data Index: 282176 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.5311. Min Act: -0.0000

Data Index: 41076 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1049160 (The Pile)

Max Activating Token Index: 244

Text #15

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1741313 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1609102 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.5768. Min Act: -0.0000

Data Index: 291612 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1646448 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 1.2987. Min Range: -1.2987

Max Act: 0.3788. Min Act: -0.0000

Data Index: 406632 (The Pile)

Max Activating Token Index: 896