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

Dataset: The Pile

Neuron 2807 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.5087. Min Act: -0.0000

Data Index: 1516076 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.5878. Min Act: -0.0000

Data Index: 692213 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.5875. Min Act: -0.0000

Data Index: 685240 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.5388. Min Act: -0.0000

Data Index: 1534899 (The Pile)

Max Activating Token Index: 529

Text #4

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.5445. Min Act: -0.0000

Data Index: 1993933 (The Pile)

Max Activating Token Index: 314

Text #5

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.5837. Min Act: -0.0000

Data Index: 12790 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.5535. Min Act: -0.0000

Data Index: 1427154 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1465577 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.4574. Min Act: -0.0000

Data Index: 1093961 (The Pile)

Max Activating Token Index: 576

Text #9

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.4301. Min Act: -0.0000

Data Index: 482042 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.3298. Min Act: -0.0000

Data Index: 353307 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.3232. Min Act: -0.0000

Data Index: 281937 (The Pile)

Max Activating Token Index: 1012

Text #12

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.2614. Min Act: -0.0000

Data Index: 1167493 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1224270 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.3138. Min Act: -0.0000

Data Index: 166878 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1652028 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.3001. Min Act: -0.0000

Data Index: 908783 (The Pile)

Max Activating Token Index: 195

Text #17

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.2045. Min Act: -0.0000

Data Index: 304571 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.2075. Min Act: -0.0000

Data Index: 350972 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.1728. Min Act: -0.0000

Data Index: 271217 (The Pile)

Max Activating Token Index: 876