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

Dataset: The Pile

Neuron 1895 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: 1.0136. Min Range: -1.0136

Max Act: 1.0136. Min Act: -0.0000

Data Index: 892114 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8673. Min Act: -0.0000

Data Index: 283154 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1842999 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8470. Min Act: -0.0000

Data Index: 330248 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.9062. Min Act: -0.0000

Data Index: 247458 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1999814 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8612. Min Act: -0.0000

Data Index: 64400 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8314. Min Act: -0.0000

Data Index: 811746 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7899. Min Act: -0.0000

Data Index: 1976078 (The Pile)

Max Activating Token Index: 518

Text #9

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1507226 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.8093. Min Act: -0.0000

Data Index: 922886 (The Pile)

Max Activating Token Index: 61

Text #11

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5894. Min Act: -0.0000

Data Index: 927985 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1289203 (The Pile)

Max Activating Token Index: 395

Text #13

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1281378 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7325. Min Act: -0.0000

Data Index: 869093 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6068. Min Act: -0.0000

Data Index: 272195 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.6407. Min Act: -0.0000

Data Index: 1244163 (The Pile)

Max Activating Token Index: 756

Text #17

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.5965. Min Act: -0.0000

Data Index: 869944 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1314792 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 1.0136. Min Range: -1.0136

Max Act: 0.7465. Min Act: -0.0000

Data Index: 566190 (The Pile)

Max Activating Token Index: 968