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

Dataset: The Pile

Neuron 1630 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: 0.8927. Min Range: -0.8927

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1716578 (The Pile)

Max Activating Token Index: 891

Text #1

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1057025 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8576. Min Act: -0.0000

Data Index: 203235 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7179. Min Act: -0.0000

Data Index: 461559 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1431388 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1751539 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1721119 (The Pile)

Max Activating Token Index: 810

Text #7

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.7938. Min Act: -0.0000

Data Index: 936967 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8172. Min Act: -0.0000

Data Index: 657338 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.8894. Min Act: -0.0000

Data Index: 585212 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6863. Min Act: -0.0000

Data Index: 860422 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1547148 (The Pile)

Max Activating Token Index: 763

Text #12

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6811. Min Act: -0.0000

Data Index: 399959 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5242. Min Act: -0.0000

Data Index: 298602 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1942332 (The Pile)

Max Activating Token Index: 308

Text #15

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1440373 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.6222. Min Act: -0.0000

Data Index: 237321 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5884. Min Act: -0.0000

Data Index: 592475 (The Pile)

Max Activating Token Index: 968

Text #18

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5737. Min Act: -0.0000

Data Index: 329331 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 0.8927. Min Range: -0.8927

Max Act: 0.5145. Min Act: -0.0000

Data Index: 848656 (The Pile)

Max Activating Token Index: 711