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

Dataset: The Pile

Neuron 3324 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: 0.6469. Min Range: -0.6469

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1557085 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.6469. Min Act: -0.0000

Data Index: 135689 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5218. Min Act: -0.0000

Data Index: 847983 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5546. Min Act: -0.0000

Data Index: 157864 (The Pile)

Max Activating Token Index: 238

Text #4

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1567719 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5178. Min Act: -0.0000

Data Index: 540988 (The Pile)

Max Activating Token Index: 656

Text #6

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1879414 (The Pile)

Max Activating Token Index: 840

Text #7

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1312810 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5112. Min Act: -0.0000

Data Index: 452359 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1728634 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1819304 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1690913 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4828. Min Act: -0.0000

Data Index: 141590 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4993. Min Act: -0.0000

Data Index: 792639 (The Pile)

Max Activating Token Index: 135

Text #14

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4971. Min Act: -0.0000

Data Index: 260878 (The Pile)

Max Activating Token Index: 317

Text #15

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4941. Min Act: -0.0000

Data Index: 115039 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4921. Min Act: -0.0000

Data Index: 225497 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1839723 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1161929 (The Pile)

Max Activating Token Index: 353

Text #19

Max Range: 0.6469. Min Range: -0.6469

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1361995 (The Pile)

Max Activating Token Index: 386