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

Dataset: The Pile

Neuron 4899 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.9962. Min Act: -0.0000

Data Index: 605275 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7426. Min Act: -0.0000

Data Index: 695847 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7091. Min Act: -0.0000

Data Index: 193927 (The Pile)

Max Activating Token Index: 628

Text #3

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6240. Min Act: -0.0000

Data Index: 870899 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6325. Min Act: -0.0000

Data Index: 1087809 (The Pile)

Max Activating Token Index: 497

Text #5

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1806959 (The Pile)

Max Activating Token Index: 4

Text #6

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1571080 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1289826 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1919159 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1341658 (The Pile)

Max Activating Token Index: 783

Text #10

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1737008 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5873. Min Act: -0.0000

Data Index: 690203 (The Pile)

Max Activating Token Index: 319

Text #12

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1083785 (The Pile)

Max Activating Token Index: 128

Text #13

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6101. Min Act: -0.0000

Data Index: 218255 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1099440 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5694. Min Act: -0.0000

Data Index: 906099 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5467. Min Act: -0.0000

Data Index: 455697 (The Pile)

Max Activating Token Index: 11

Text #17

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5615. Min Act: -0.0000

Data Index: 238210 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5941. Min Act: -0.0000

Data Index: 925426 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1159418 (The Pile)

Max Activating Token Index: 13