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

Dataset: The Pile

Neuron 1718 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: 1.1219. Min Range: -1.1219

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1282845 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.9162. Min Act: -0.0000

Data Index: 84471 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1145347 (The Pile)

Max Activating Token Index: 926

Text #3

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8025. Min Act: -0.0000

Data Index: 188939 (The Pile)

Max Activating Token Index: 537

Text #4

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1913098 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8080. Min Act: -0.0000

Data Index: 888699 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8338. Min Act: -0.0000

Data Index: 235643 (The Pile)

Max Activating Token Index: 367

Text #7

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1587353 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8087. Min Act: -0.0000

Data Index: 560206 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1000475 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1938568 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.7169. Min Act: -0.0000

Data Index: 302503 (The Pile)

Max Activating Token Index: 1020

Text #12

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.7099. Min Act: -0.0000

Data Index: 756998 (The Pile)

Max Activating Token Index: 910

Text #13

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.6098. Min Act: -0.0000

Data Index: 127393 (The Pile)

Max Activating Token Index: 779

Text #14

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1177331 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.6664. Min Act: -0.0000

Data Index: 468628 (The Pile)

Max Activating Token Index: 720

Text #16

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1361200 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.6999. Min Act: -0.0000

Data Index: 516171 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.6960. Min Act: -0.0000

Data Index: 151824 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1932967 (The Pile)

Max Activating Token Index: 633