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

Dataset: The Pile

Neuron 1228 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: 0.7518. Min Range: -0.7518

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1475025 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1933991 (The Pile)

Max Activating Token Index: 710

Text #2

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6612. Min Act: -0.0000

Data Index: 819756 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6991. Min Act: -0.0000

Data Index: 908089 (The Pile)

Max Activating Token Index: 866

Text #4

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1129520 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6693. Min Act: -0.0000

Data Index: 199086 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1010118 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1183518 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5963. Min Act: -0.0000

Data Index: 746990 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6077. Min Act: -0.0000

Data Index: 84645 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1019629 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5972. Min Act: -0.0000

Data Index: 561079 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1843036 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1489422 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5660. Min Act: -0.0000

Data Index: 44742 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5837. Min Act: -0.0000

Data Index: 663240 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5960. Min Act: -0.0000

Data Index: 570972 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5425. Min Act: -0.0000

Data Index: 368270 (The Pile)

Max Activating Token Index: 144

Text #18

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5903. Min Act: -0.0000

Data Index: 987056 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 0.7518. Min Range: -0.7518

Max Act: 0.5254. Min Act: -0.0000

Data Index: 343949 (The Pile)

Max Activating Token Index: 849