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

Dataset: The Pile

Neuron 1063 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1079219 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1565986 (The Pile)

Max Activating Token Index: 967

Text #2

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5918. Min Act: -0.0000

Data Index: 200301 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1898128 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5273. Min Act: -0.0000

Data Index: 401007 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4843. Min Act: -0.0000

Data Index: 106095 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5106. Min Act: -0.0000

Data Index: 179445 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1465655 (The Pile)

Max Activating Token Index: 271

Text #8

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4923. Min Act: -0.0000

Data Index: 597614 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4923. Min Act: -0.0000

Data Index: 160439 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4464. Min Act: -0.0000

Data Index: 890172 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1587469 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1111875 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4435. Min Act: -0.0000

Data Index: 507568 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1869021 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4501. Min Act: -0.0000

Data Index: 45262 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4458. Min Act: -0.0000

Data Index: 723678 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5321. Min Act: -0.0000

Data Index: 963903 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1172059 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4213. Min Act: -0.0000

Data Index: 375967 (The Pile)

Max Activating Token Index: 534