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

Dataset: The Pile

Neuron 635 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.3666. Min Act: -0.0000

Data Index: 1953331 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1619789 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0936. Min Act: -0.0000

Data Index: 1123289 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9951. Min Act: -0.0000

Data Index: 19282 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1164877 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1943232 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1200259 (The Pile)

Max Activating Token Index: 165

Text #7

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9039. Min Act: -0.0000

Data Index: 42173 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9871. Min Act: -0.0000

Data Index: 395044 (The Pile)

Max Activating Token Index: 145

Text #9

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1464998 (The Pile)

Max Activating Token Index: 356

Text #10

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1181013 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0509. Min Act: -0.0000

Data Index: 349498 (The Pile)

Max Activating Token Index: 596

Text #12

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0133. Min Act: -0.0000

Data Index: 614537 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1649896 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0988. Min Act: -0.0000

Data Index: 807427 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9643. Min Act: -0.0000

Data Index: 760322 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 1.3666. Min Range: -1.3666

Max Act: 1.0287. Min Act: -0.0000

Data Index: 285638 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.9386. Min Act: -0.0000

Data Index: 912156 (The Pile)

Max Activating Token Index: 258

Text #18

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8805. Min Act: -0.0000

Data Index: 54492 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 1.3666. Min Range: -1.3666

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1126247 (The Pile)

Max Activating Token Index: 943