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

Dataset: The Pile

Neuron 4030 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3212. Min Range: -1.3212

Max Act: 1.3212. Min Act: -0.0000

Data Index: 1993693 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 1.3212. Min Range: -1.3212

Max Act: 1.1853. Min Act: -0.0000

Data Index: 175279 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 1.3212. Min Range: -1.3212

Max Act: 1.2956. Min Act: -0.0000

Data Index: 1949405 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9742. Min Act: -0.0000

Data Index: 681662 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1684169 (The Pile)

Max Activating Token Index: 63

Text #5

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1926279 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9216. Min Act: -0.0000

Data Index: 656491 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1173781 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1062564 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9009. Min Act: -0.0000

Data Index: 382870 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1683208 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8795. Min Act: -0.0000

Data Index: 276454 (The Pile)

Max Activating Token Index: 66

Text #12

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8161. Min Act: -0.0000

Data Index: 13812 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8328. Min Act: -0.0000

Data Index: 228553 (The Pile)

Max Activating Token Index: 932

Text #14

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8563. Min Act: -0.0000

Data Index: 499887 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8504. Min Act: -0.0000

Data Index: 404921 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.7712. Min Act: -0.0000

Data Index: 894635 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.7786. Min Act: -0.0000

Data Index: 64260 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1285913 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.7710. Min Act: -0.0000

Data Index: 425764 (The Pile)

Max Activating Token Index: 352