Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 520 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5754. Min Act: -0.0000

Data Index: 811211 (The Pile)

Max Activating Token Index: 816

Text #1

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1272177 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5383. Min Act: -0.0000

Data Index: 1567007 (The Pile)

Max Activating Token Index: 762

Text #3

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5224. Min Act: -0.0000

Data Index: 459931 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1613238 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4700. Min Act: -0.0000

Data Index: 870964 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5136. Min Act: -0.0000

Data Index: 516307 (The Pile)

Max Activating Token Index: 177

Text #7

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5220. Min Act: -0.0000

Data Index: 584290 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4996. Min Act: -0.0000

Data Index: 596027 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5609. Min Act: -0.0000

Data Index: 1437294 (The Pile)

Max Activating Token Index: 745

Text #10

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5271. Min Act: -0.0000

Data Index: 448905 (The Pile)

Max Activating Token Index: 172

Text #11

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1269283 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1855988 (The Pile)

Max Activating Token Index: 600

Text #13

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4889. Min Act: -0.0000

Data Index: 374531 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1272637 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4941. Min Act: -0.0000

Data Index: 1793438 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1963086 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4905. Min Act: -0.0000

Data Index: 826886 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4708. Min Act: -0.0000

Data Index: 901658 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 0.5762. Min Range: -0.5762

Max Act: 0.4823. Min Act: -0.0000

Data Index: 913561 (The Pile)

Max Activating Token Index: 165