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

Dataset: The Pile

Neuron 924 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: 1.8049. Min Range: -1.8049

Max Act: 1.8049. Min Act: -0.0000

Data Index: 1430790 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.7509. Min Act: -0.0000

Data Index: 301688 (The Pile)

Max Activating Token Index: 384

Text #2

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.7064. Min Act: -0.0000

Data Index: 1984234 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.6161. Min Act: -0.0000

Data Index: 687630 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5376. Min Act: -0.0000

Data Index: 889363 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4762. Min Act: -0.0000

Data Index: 1741092 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4941. Min Act: -0.0000

Data Index: 272559 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1513247 (The Pile)

Max Activating Token Index: 206

Text #8

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4279. Min Act: -0.0000

Data Index: 96550 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.2318. Min Act: -0.0000

Data Index: 1045805 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4595. Min Act: -0.0000

Data Index: 1835237 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3682. Min Act: -0.0000

Data Index: 891810 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3179. Min Act: -0.0000

Data Index: 913732 (The Pile)

Max Activating Token Index: 407

Text #13

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4323. Min Act: -0.0000

Data Index: 373747 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.2804. Min Act: -0.0000

Data Index: 400684 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3443. Min Act: -0.0000

Data Index: 1162740 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4153. Min Act: -0.0000

Data Index: 922197 (The Pile)

Max Activating Token Index: 165

Text #17

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.3175. Min Act: -0.0000

Data Index: 1693472 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.2419. Min Act: -0.0000

Data Index: 1051189 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.2278. Min Act: -0.0000

Data Index: 115107 (The Pile)

Max Activating Token Index: 390