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

Dataset: The Pile

Neuron 2254 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.8712. Min Act: -0.0000

Data Index: 281758 (The Pile)

Max Activating Token Index: 134

Text #1

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7715. Min Act: -0.0000

Data Index: 142688 (The Pile)

Max Activating Token Index: 430

Text #2

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7803. Min Act: -0.0000

Data Index: 662399 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.7219. Min Act: -0.0000

Data Index: 896337 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1800141 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6702. Min Act: -0.0000

Data Index: 187924 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1667167 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1166284 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6068. Min Act: -0.0000

Data Index: 470179 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1337367 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1585203 (The Pile)

Max Activating Token Index: 995

Text #11

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1022621 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1860860 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6150. Min Act: 0.0000

Data Index: 255229 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6138. Min Act: -0.0000

Data Index: 552816 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6103. Min Act: -0.0000

Data Index: 87193 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1133961 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1225669 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1933284 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 0.8712. Min Range: -0.8712

Max Act: 0.5958. Min Act: -0.0000

Data Index: 579704 (The Pile)

Max Activating Token Index: 578