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

Dataset: The Pile

Neuron 1544 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: 0.9027. Min Range: -0.9027

Max Act: 0.9027. Min Act: -0.0000

Data Index: 484357 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1498208 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8252. Min Act: -0.0000

Data Index: 749658 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8542. Min Act: -0.0000

Data Index: 568075 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8101. Min Act: -0.0000

Data Index: 935306 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7554. Min Act: -0.0000

Data Index: 457413 (The Pile)

Max Activating Token Index: 47

Text #6

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1228176 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1365925 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7318. Min Act: -0.0000

Data Index: 601588 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7780. Min Act: -0.0000

Data Index: 1933553 (The Pile)

Max Activating Token Index: 452

Text #10

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6969. Min Act: -0.0000

Data Index: 60354 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6900. Min Act: -0.0000

Data Index: 916634 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1005544 (The Pile)

Max Activating Token Index: 212

Text #13

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1693451 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1427907 (The Pile)

Max Activating Token Index: 304

Text #15

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1858021 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1248818 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1172425 (The Pile)

Max Activating Token Index: 326

Text #18

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1592012 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 0.9027. Min Range: -0.9027

Max Act: 0.8054. Min Act: -0.0000

Data Index: 297314 (The Pile)

Max Activating Token Index: 60