Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1106 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.8567. Min Act: -0.0000

Data Index: 1675683 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.8623. Min Act: -0.0000

Data Index: 1084360 (The Pile)

Max Activating Token Index: 771

Text #2

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.7067. Min Act: -0.0000

Data Index: 887377 (The Pile)

Max Activating Token Index: 566

Text #3

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6922. Min Act: -0.0000

Data Index: 1578192 (The Pile)

Max Activating Token Index: 280

Text #4

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6323. Min Act: -0.0000

Data Index: 152810 (The Pile)

Max Activating Token Index: 628

Text #5

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6325. Min Act: -0.0000

Data Index: 282878 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6707. Min Act: -0.0000

Data Index: 839030 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.7673. Min Act: -0.0000

Data Index: 1793244 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5137. Min Act: -0.0000

Data Index: 98953 (The Pile)

Max Activating Token Index: 672

Text #9

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6910. Min Act: -0.0000

Data Index: 543216 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1175258 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5143. Min Act: -0.0000

Data Index: 1516744 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5925. Min Act: -0.0000

Data Index: 1654780 (The Pile)

Max Activating Token Index: 274

Text #13

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4788. Min Act: -0.0000

Data Index: 1092919 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.3605. Min Act: -0.0000

Data Index: 572462 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4557. Min Act: -0.0000

Data Index: 906590 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4448. Min Act: -0.0000

Data Index: 500214 (The Pile)

Max Activating Token Index: 70

Text #17

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4268. Min Act: -0.0000

Data Index: 906116 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1839622 (The Pile)

Max Activating Token Index: 537

Text #19

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.3938. Min Act: -0.0000

Data Index: 182874 (The Pile)

Max Activating Token Index: 18