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

Dataset: The Pile

Neuron 402 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: 0.9889. Min Range: -0.9889

Max Act: 0.9889. Min Act: -0.0000

Data Index: 474703 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.9532. Min Act: -0.0000

Data Index: 106637 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1108284 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1014581 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1266015 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1027426 (The Pile)

Max Activating Token Index: 404

Text #6

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.8881. Min Act: -0.0000

Data Index: 1758078 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7399. Min Act: -0.0000

Data Index: 639960 (The Pile)

Max Activating Token Index: 196

Text #8

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1524946 (The Pile)

Max Activating Token Index: 588

Text #9

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1388103 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7864. Min Act: -0.0000

Data Index: 136331 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1145540 (The Pile)

Max Activating Token Index: 793

Text #12

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7364. Min Act: -0.0000

Data Index: 44934 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7911. Min Act: -0.0000

Data Index: 324146 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7221. Min Act: -0.0000

Data Index: 770377 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1203597 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1578553 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1854458 (The Pile)

Max Activating Token Index: 680

Text #18

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1143897 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 0.9889. Min Range: -0.9889

Max Act: 0.6037. Min Act: -0.0000

Data Index: 18606 (The Pile)

Max Activating Token Index: 619