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

Dataset: The Pile

Neuron 2337 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: 1.7971. Min Range: -1.7971

Max Act: 1.7971. Min Act: -0.0000

Data Index: 954690 (The Pile)

Max Activating Token Index: 319

Text #1

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1007033 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5498. Min Act: -0.0000

Data Index: 1616209 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5241. Min Act: -0.0000

Data Index: 182366 (The Pile)

Max Activating Token Index: 963

Text #4

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5751. Min Act: -0.0000

Data Index: 1942606 (The Pile)

Max Activating Token Index: 419

Text #5

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5156. Min Act: -0.0000

Data Index: 154512 (The Pile)

Max Activating Token Index: 127

Text #6

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.5079. Min Act: -0.0000

Data Index: 918949 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4961. Min Act: -0.0000

Data Index: 817917 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4905. Min Act: -0.0000

Data Index: 720785 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4704. Min Act: -0.0000

Data Index: 1851876 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4968. Min Act: -0.0000

Data Index: 1482321 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4552. Min Act: -0.0000

Data Index: 1749266 (The Pile)

Max Activating Token Index: 2

Text #12

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4552. Min Act: -0.0000

Data Index: 603564 (The Pile)

Max Activating Token Index: 2

Text #13

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4552. Min Act: -0.0000

Data Index: 1767182 (The Pile)

Max Activating Token Index: 2

Text #14

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4402. Min Act: -0.0000

Data Index: 1578828 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4013. Min Act: -0.0000

Data Index: 63936 (The Pile)

Max Activating Token Index: 1018

Text #16

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4012. Min Act: -0.0000

Data Index: 1435584 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1053113 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1810544 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 1.7971. Min Range: -1.7971

Max Act: 1.4177. Min Act: -0.0000

Data Index: 668347 (The Pile)

Max Activating Token Index: 743