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

Dataset: The Pile

Neuron 3353 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1153922 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1391558 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.7183. Min Act: -0.0000

Data Index: 803698 (The Pile)

Max Activating Token Index: 891

Text #3

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1165072 (The Pile)

Max Activating Token Index: 507

Text #4

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1689214 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1878988 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6661. Min Act: -0.0000

Data Index: 742758 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6470. Min Act: -0.0000

Data Index: 142137 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1221063 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6817. Min Act: -0.0000

Data Index: 476539 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1467565 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1377552 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6326. Min Act: 0.0000

Data Index: 1975088 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.5727. Min Act: 0.0000

Data Index: 680778 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1915301 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.5712. Min Act: 0.0000

Data Index: 1531934 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.5692. Min Act: -0.0000

Data Index: 57540 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.5152. Min Act: 0.0000

Data Index: 91745 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1579360 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 0.9495. Min Range: -0.9495

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1246539 (The Pile)

Max Activating Token Index: 718