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

Dataset: The Pile

Neuron 3577 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: 1.6811. Min Range: -1.6811

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1393744 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.5687. Min Act: -0.0000

Data Index: 163086 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1355980 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.5446. Min Act: -0.0000

Data Index: 1786254 (The Pile)

Max Activating Token Index: 782

Text #4

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4333. Min Act: -0.0000

Data Index: 925402 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.5183. Min Act: -0.0000

Data Index: 1879059 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3553. Min Act: -0.0000

Data Index: 1552290 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3361. Min Act: -0.0000

Data Index: 218978 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4877. Min Act: -0.0000

Data Index: 1993646 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4895. Min Act: -0.0000

Data Index: 1015732 (The Pile)

Max Activating Token Index: 954

Text #10

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4625. Min Act: -0.0000

Data Index: 536005 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4818. Min Act: -0.0000

Data Index: 1215555 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4116. Min Act: -0.0000

Data Index: 629549 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1153893 (The Pile)

Max Activating Token Index: 337

Text #14

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4446. Min Act: -0.0000

Data Index: 383289 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1931100 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2799. Min Act: -0.0000

Data Index: 1943553 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3496. Min Act: -0.0000

Data Index: 336966 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1741405 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3401. Min Act: -0.0000

Data Index: 1083325 (The Pile)

Max Activating Token Index: 414