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

Dataset: The Pile

Neuron 4155 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: 4.8233. Min Range: -4.8233

Max Act: 4.8233. Min Act: -0.0000

Data Index: 1973305 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.5367. Min Act: -0.0000

Data Index: 169704 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.4801. Min Act: -0.0000

Data Index: 199954 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.6285. Min Act: -0.0000

Data Index: 1357791 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.1873. Min Act: -0.0000

Data Index: 127328 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.2933. Min Act: -0.0000

Data Index: 18872 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.2914. Min Act: -0.0000

Data Index: 1323173 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.2821. Min Act: -0.0000

Data Index: 1945433 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.1024. Min Act: -0.0000

Data Index: 619575 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.4622. Min Act: -0.0000

Data Index: 699106 (The Pile)

Max Activating Token Index: 487

Text #10

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.1315. Min Act: -0.0000

Data Index: 1046826 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.2948. Min Act: -0.0000

Data Index: 1706807 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 4.8233. Min Range: -4.8233

Max Act: 3.9388. Min Act: -0.0000

Data Index: 1202004 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.2183. Min Act: -0.0000

Data Index: 1285834 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.3871. Min Act: -0.0000

Data Index: 1283939 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.0572. Min Act: -0.0000

Data Index: 1578765 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.2039. Min Act: -0.0000

Data Index: 1030416 (The Pile)

Max Activating Token Index: 7

Text #17

Max Range: 4.8233. Min Range: -4.8233

Max Act: 4.0119. Min Act: -0.0000

Data Index: 627740 (The Pile)

Max Activating Token Index: 498

Text #18

Max Range: 4.8233. Min Range: -4.8233

Max Act: 3.9834. Min Act: -0.0000

Data Index: 1290346 (The Pile)

Max Activating Token Index: 550

Text #19

Max Range: 4.8233. Min Range: -4.8233

Max Act: 3.8134. Min Act: -0.0000

Data Index: 664491 (The Pile)

Max Activating Token Index: 978