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

Dataset: The Pile

Neuron 3664 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: 0.5197. Min Range: -0.5197

Max Act: 0.5197. Min Act: -0.0000

Data Index: 869782 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3737. Min Act: -0.0000

Data Index: 789810 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1249789 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4187. Min Act: -0.0000

Data Index: 860405 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1635553 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4216. Min Act: -0.0000

Data Index: 383092 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.4055. Min Act: -0.0000

Data Index: 773909 (The Pile)

Max Activating Token Index: 830

Text #7

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3836. Min Act: -0.0000

Data Index: 73297 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3214. Min Act: -0.0000

Data Index: 663289 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3615. Min Act: -0.0000

Data Index: 889206 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3480. Min Act: -0.0000

Data Index: 704119 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3360. Min Act: -0.0000

Data Index: 379723 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1360361 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3079. Min Act: -0.0000

Data Index: 447450 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3291. Min Act: -0.0000

Data Index: 696950 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3167. Min Act: -0.0000

Data Index: 612373 (The Pile)

Max Activating Token Index: 249

Text #16

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1962569 (The Pile)

Max Activating Token Index: 281

Text #17

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3372. Min Act: -0.0000

Data Index: 335115 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3234. Min Act: -0.0000

Data Index: 636413 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3037. Min Act: -0.0000

Data Index: 157576 (The Pile)

Max Activating Token Index: 79