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

Dataset: The Pile

Neuron 4995 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: 1.1674. Min Range: -1.1674

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1354413 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7833. Min Act: -0.0000

Data Index: 225866 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1012618 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7586. Min Act: -0.0000

Data Index: 140562 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1422407 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1040825 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.6453. Min Act: -0.0000

Data Index: 787358 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.6767. Min Act: -0.0000

Data Index: 1162401 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.7010. Min Act: -0.0000

Data Index: 808104 (The Pile)

Max Activating Token Index: 763

Text #9

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1108671 (The Pile)

Max Activating Token Index: 889

Text #10

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1219171 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.5736. Min Act: -0.0000

Data Index: 142345 (The Pile)

Max Activating Token Index: 840

Text #12

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.6225. Min Act: -0.0000

Data Index: 858844 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1924105 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1904903 (The Pile)

Max Activating Token Index: 854

Text #15

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.5361. Min Act: -0.0000

Data Index: 6239 (The Pile)

Max Activating Token Index: 832

Text #16

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.5620. Min Act: -0.0000

Data Index: 349304 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.5237. Min Act: -0.0000

Data Index: 29877 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.5042. Min Act: -0.0000

Data Index: 878088 (The Pile)

Max Activating Token Index: 695

Text #19

Max Range: 1.1674. Min Range: -1.1674

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1855325 (The Pile)

Max Activating Token Index: 853