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

Dataset: The Pile

Neuron 1176 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.9033. Min Act: -0.0000

Data Index: 35141 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1055810 (The Pile)

Max Activating Token Index: 233

Text #2

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8045. Min Act: -0.0000

Data Index: 792934 (The Pile)

Max Activating Token Index: 102

Text #3

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1606362 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1918851 (The Pile)

Max Activating Token Index: 796

Text #5

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1901310 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7686. Min Act: -0.0000

Data Index: 948427 (The Pile)

Max Activating Token Index: 574

Text #7

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1429457 (The Pile)

Max Activating Token Index: 38

Text #8

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7878. Min Act: -0.0000

Data Index: 785043 (The Pile)

Max Activating Token Index: 418

Text #9

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1042711 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7420. Min Act: -0.0000

Data Index: 712542 (The Pile)

Max Activating Token Index: 961

Text #11

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1103559 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1931628 (The Pile)

Max Activating Token Index: 797

Text #13

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7328. Min Act: -0.0000

Data Index: 734220 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1836028 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1053375 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1377039 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6702. Min Act: -0.0000

Data Index: 222721 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1284912 (The Pile)

Max Activating Token Index: 193

Text #19

Max Range: 0.9033. Min Range: -0.9033

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1405885 (The Pile)

Max Activating Token Index: 808