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

Dataset: The Pile

Neuron 1191 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: 0.7070. Min Range: -0.7070

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1148878 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5808. Min Act: -0.0000

Data Index: 860184 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1316548 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6317. Min Act: -0.0000

Data Index: 352418 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1205880 (The Pile)

Max Activating Token Index: 339

Text #5

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1512185 (The Pile)

Max Activating Token Index: 189

Text #6

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6331. Min Act: -0.0000

Data Index: 21926 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1293639 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1849274 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.6125. Min Act: -0.0000

Data Index: 41054 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1864497 (The Pile)

Max Activating Token Index: 324

Text #11

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5585. Min Act: -0.0000

Data Index: 50774 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5971. Min Act: -0.0000

Data Index: 482642 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5210. Min Act: -0.0001

Data Index: 1513012 (The Pile)

Max Activating Token Index: 781

Text #14

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1151145 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5584. Min Act: -0.0000

Data Index: 672336 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1350661 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5057. Min Act: -0.0000

Data Index: 565182 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5446. Min Act: -0.0000

Data Index: 899389 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 0.7070. Min Range: -0.7070

Max Act: 0.5590. Min Act: -0.0000

Data Index: 441136 (The Pile)

Max Activating Token Index: 97