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

Dataset: The Pile

Neuron 2758 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: 0.5176. Min Range: -0.5176

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1490713 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1749617 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.5176. Min Act: -0.0000

Data Index: 616008 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1875304 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4282. Min Act: -0.0000

Data Index: 963509 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1457682 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4007. Min Act: -0.0000

Data Index: 320890 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1731893 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1162952 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3785. Min Act: -0.0000

Data Index: 58411 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1868878 (The Pile)

Max Activating Token Index: 360

Text #11

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.4121. Min Act: -0.0000

Data Index: 1625968 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3917. Min Act: -0.0000

Data Index: 927051 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1554862 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1400957 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3543. Min Act: -0.0000

Data Index: 158502 (The Pile)

Max Activating Token Index: 762

Text #16

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3701. Min Act: -0.0000

Data Index: 755872 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3262. Min Act: -0.0000

Data Index: 506121 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3796. Min Act: -0.0000

Data Index: 214309 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 0.5176. Min Range: -0.5176

Max Act: 0.3480. Min Act: -0.0000

Data Index: 83354 (The Pile)

Max Activating Token Index: 152