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

Dataset: The Pile

Neuron 2211 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: 0.7103. Min Range: -0.7103

Max Act: 0.7103. Min Act: -0.0000

Data Index: 830554 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4420. Min Act: -0.0000

Data Index: 707265 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.4636. Min Act: -0.0000

Data Index: 856264 (The Pile)

Max Activating Token Index: 1009

Text #3

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3684. Min Act: -0.0000

Data Index: 1252651 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1414632 (The Pile)

Max Activating Token Index: 724

Text #5

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3471. Min Act: -0.0000

Data Index: 635341 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1383533 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1463130 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1604931 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3371. Min Act: -0.0000

Data Index: 184958 (The Pile)

Max Activating Token Index: 93

Text #10

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3139. Min Act: -0.0000

Data Index: 79377 (The Pile)

Max Activating Token Index: 199

Text #11

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1968791 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3420. Min Act: -0.0000

Data Index: 812496 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1838350 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3061. Min Act: -0.0000

Data Index: 680992 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1802830 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1844682 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.2962. Min Act: -0.0000

Data Index: 821367 (The Pile)

Max Activating Token Index: 962

Text #18

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3059. Min Act: -0.0000

Data Index: 1889138 (The Pile)

Max Activating Token Index: 1004

Text #19

Max Range: 0.7103. Min Range: -0.7103

Max Act: 0.3113. Min Act: -0.0000

Data Index: 1281555 (The Pile)

Max Activating Token Index: 566