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

Dataset: The Pile

Neuron 1187 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: 1.0904. Min Range: -1.0904

Max Act: 1.0904. Min Act: -0.0000

Data Index: 885452 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.9572. Min Act: -0.0000

Data Index: 1153931 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1395847 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8722. Min Act: -0.0000

Data Index: 920056 (The Pile)

Max Activating Token Index: 641

Text #4

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8590. Min Act: -0.0000

Data Index: 667021 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1076868 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8442. Min Act: -0.0000

Data Index: 811972 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1644477 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1447462 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1903235 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7063. Min Act: -0.0000

Data Index: 822046 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7951. Min Act: -0.0000

Data Index: 673749 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7502. Min Act: -0.0000

Data Index: 230016 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8665. Min Act: -0.0000

Data Index: 299161 (The Pile)

Max Activating Token Index: 706

Text #14

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7688. Min Act: -0.0000

Data Index: 647464 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.8154. Min Act: -0.0000

Data Index: 592093 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1398792 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1003059 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7694. Min Act: -0.0000

Data Index: 405786 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 1.0904. Min Range: -1.0904

Max Act: 0.7586. Min Act: -0.0000

Data Index: 297825 (The Pile)

Max Activating Token Index: 417