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

Dataset: The Pile

Neuron 203 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1898445 (The Pile)

Max Activating Token Index: 600

Text #1

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.9677. Min Act: -0.0000

Data Index: 1357535 (The Pile)

Max Activating Token Index: 495

Text #2

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1891226 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1488093 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1886107 (The Pile)

Max Activating Token Index: 257

Text #5

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.7748. Min Act: -0.0000

Data Index: 999008 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.8451. Min Act: -0.0000

Data Index: 1994025 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.8340. Min Act: -0.0000

Data Index: 96190 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.7595. Min Act: -0.0000

Data Index: 290963 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1963265 (The Pile)

Max Activating Token Index: 220

Text #10

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.7262. Min Act: -0.0000

Data Index: 548235 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.7989. Min Act: -0.0000

Data Index: 104768 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.7316. Min Act: -0.0000

Data Index: 568398 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.7190. Min Act: -0.0000

Data Index: 635193 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.6513. Min Act: -0.0000

Data Index: 950832 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.6875. Min Act: -0.0000

Data Index: 927448 (The Pile)

Max Activating Token Index: 475

Text #16

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1185049 (The Pile)

Max Activating Token Index: 788

Text #17

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.6447. Min Act: -0.0000

Data Index: 1036234 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1709904 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 0.9677. Min Range: -0.9677

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1377054 (The Pile)

Max Activating Token Index: 787