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

Dataset: The Pile

Neuron 804 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: 0.4399. Min Range: -0.4399

Max Act: 0.4399. Min Act: -0.0000

Data Index: 617098 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3572. Min Act: -0.0000

Data Index: 488769 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1290969 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3831. Min Act: -0.0000

Data Index: 1080844 (The Pile)

Max Activating Token Index: 954

Text #4

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.4128. Min Act: -0.0000

Data Index: 921621 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1070117 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1169929 (The Pile)

Max Activating Token Index: 983

Text #7

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3260. Min Act: -0.0000

Data Index: 72502 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1313147 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3061. Min Act: -0.0000

Data Index: 104475 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3686. Min Act: -0.0000

Data Index: 123065 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1008036 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.2800. Min Act: -0.0000

Data Index: 113153 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1542293 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1567339 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.2888. Min Act: -0.0000

Data Index: 364811 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1852554 (The Pile)

Max Activating Token Index: 588

Text #17

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1778001 (The Pile)

Max Activating Token Index: 306

Text #18

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.2763. Min Act: -0.0000

Data Index: 917124 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.4399. Min Range: -0.4399

Max Act: 0.2774. Min Act: -0.0000

Data Index: 453642 (The Pile)

Max Activating Token Index: 584