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

Dataset: The Pile

Neuron 2770 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2923. Min Range: -1.2923

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1735129 (The Pile)

Max Activating Token Index: 155

Text #1

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.9670. Min Act: -0.0000

Data Index: 667213 (The Pile)

Max Activating Token Index: 819

Text #2

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.7913. Min Act: -0.0000

Data Index: 838656 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.7438. Min Act: -0.0000

Data Index: 611902 (The Pile)

Max Activating Token Index: 987

Text #4

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1142487 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.7578. Min Act: -0.0000

Data Index: 539562 (The Pile)

Max Activating Token Index: 260

Text #6

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1411491 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6708. Min Act: -0.0000

Data Index: 261886 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1371747 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6683. Min Act: -0.0000

Data Index: 1025858 (The Pile)

Max Activating Token Index: 100

Text #10

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1418561 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.7037. Min Act: 0.0000

Data Index: 1579545 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1924825 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1970363 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6372. Min Act: -0.0000

Data Index: 522179 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6016. Min Act: -0.0000

Data Index: 812988 (The Pile)

Max Activating Token Index: 170

Text #16

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6316. Min Act: -0.0000

Data Index: 847898 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6223. Min Act: 0.0000

Data Index: 513048 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1720637 (The Pile)

Max Activating Token Index: 435

Text #19

Max Range: 1.2923. Min Range: -1.2923

Max Act: 0.6097. Min Act: -0.0000

Data Index: 608792 (The Pile)

Max Activating Token Index: 928