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

Dataset: The Pile

Neuron 2907 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: 0.8433. Min Range: -0.8433

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1149707 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1965775 (The Pile)

Max Activating Token Index: 55

Text #2

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1029833 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.8433. Min Act: -0.0000

Data Index: 772768 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1872405 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1587826 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.8025. Min Act: -0.0000

Data Index: 501647 (The Pile)

Max Activating Token Index: 143

Text #7

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7789. Min Act: -0.0000

Data Index: 133657 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7870. Min Act: -0.0000

Data Index: 198032 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7214. Min Act: -0.0000

Data Index: 564367 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7483. Min Act: -0.0000

Data Index: 112494 (The Pile)

Max Activating Token Index: 858

Text #11

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7198. Min Act: -0.0000

Data Index: 281667 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7339. Min Act: -0.0000

Data Index: 900104 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6760. Min Act: -0.0000

Data Index: 20068 (The Pile)

Max Activating Token Index: 721

Text #14

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1065635 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1934200 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7175. Min Act: -0.0000

Data Index: 230491 (The Pile)

Max Activating Token Index: 340

Text #17

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1913931 (The Pile)

Max Activating Token Index: 642

Text #18

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1402806 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 0.8433. Min Range: -0.8433

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1052151 (The Pile)

Max Activating Token Index: 162