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

Dataset: The Pile

Neuron 4116 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: 1.0177. Min Range: -1.0177

Max Act: 1.0177. Min Act: -0.0000

Data Index: 648290 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9799. Min Act: -0.0000

Data Index: 445960 (The Pile)

Max Activating Token Index: 516

Text #2

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.9361. Min Act: -0.0000

Data Index: 119050 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8996. Min Act: -0.0000

Data Index: 267748 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1265758 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1409972 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7406. Min Act: -0.0000

Data Index: 485657 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1928773 (The Pile)

Max Activating Token Index: 341

Text #8

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.8122. Min Act: -0.0000

Data Index: 233871 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7215. Min Act: -0.0000

Data Index: 477786 (The Pile)

Max Activating Token Index: 520

Text #10

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1360059 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1060311 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.6925. Min Act: -0.0000

Data Index: 76791 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7015. Min Act: -0.0000

Data Index: 466613 (The Pile)

Max Activating Token Index: 541

Text #14

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1522483 (The Pile)

Max Activating Token Index: 969

Text #15

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1893675 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1849901 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1614576 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1597334 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 1.0177. Min Range: -1.0177

Max Act: 0.6958. Min Act: -0.0000

Data Index: 253399 (The Pile)

Max Activating Token Index: 132