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

Dataset: The Pile

Neuron 3099 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6873. Min Act: -0.0000

Data Index: 375081 (The Pile)

Max Activating Token Index: 418

Text #1

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6658. Min Act: -0.0000

Data Index: 400224 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6557. Min Act: -0.0000

Data Index: 179448 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1109054 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1238438 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6220. Min Act: -0.0000

Data Index: 933234 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6228. Min Act: -0.0000

Data Index: 691077 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1021907 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6259. Min Act: -0.0000

Data Index: 832956 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1368089 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6034. Min Act: -0.0000

Data Index: 397809 (The Pile)

Max Activating Token Index: 427

Text #11

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5812. Min Act: -0.0000

Data Index: 991915 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6116. Min Act: -0.0000

Data Index: 597940 (The Pile)

Max Activating Token Index: 22

Text #13

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1387342 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5741. Min Act: -0.0000

Data Index: 124980 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1031915 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.6008. Min Act: -0.0000

Data Index: 370950 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5794. Min Act: -0.0000

Data Index: 877107 (The Pile)

Max Activating Token Index: 577

Text #18

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1646979 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 0.6873. Min Range: -0.6873

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1068986 (The Pile)

Max Activating Token Index: 244