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

Dataset: The Pile

Neuron 4517 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: 1.7709. Min Range: -1.7709

Max Act: 1.7709. Min Act: -0.0000

Data Index: 1569147 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.5316. Min Act: -0.0000

Data Index: 89824 (The Pile)

Max Activating Token Index: 71

Text #2

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.5530. Min Act: -0.0000

Data Index: 1122301 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.5542. Min Act: -0.0000

Data Index: 1282344 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4651. Min Act: -0.0000

Data Index: 1596069 (The Pile)

Max Activating Token Index: 74

Text #5

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.3838. Min Act: -0.0000

Data Index: 550614 (The Pile)

Max Activating Token Index: 102

Text #6

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.3888. Min Act: -0.0000

Data Index: 358320 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4541. Min Act: -0.0000

Data Index: 1292163 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4561. Min Act: -0.0000

Data Index: 158870 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.5100. Min Act: -0.0000

Data Index: 12737 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.3500. Min Act: -0.0000

Data Index: 498054 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.3848. Min Act: -0.0000

Data Index: 1830824 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.3810. Min Act: -0.0000

Data Index: 1003603 (The Pile)

Max Activating Token Index: 202

Text #13

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4523. Min Act: -0.0000

Data Index: 1840290 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4503. Min Act: -0.0000

Data Index: 625126 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1284844 (The Pile)

Max Activating Token Index: 140

Text #16

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4707. Min Act: -0.0000

Data Index: 780531 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.2819. Min Act: -0.0000

Data Index: 1946904 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1140669 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 1.7709. Min Range: -1.7709

Max Act: 1.4099. Min Act: -0.0000

Data Index: 913009 (The Pile)

Max Activating Token Index: 215