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

Dataset: The Pile

Neuron 4899 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: 0.3760. Min Range: -0.3760

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1963573 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1449671 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1804739 (The Pile)

Max Activating Token Index: 115

Text #3

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1085247 (The Pile)

Max Activating Token Index: 129

Text #4

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2774. Min Act: -0.0000

Data Index: 27749 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1601482 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1998609 (The Pile)

Max Activating Token Index: 777

Text #7

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2806. Min Act: -0.0000

Data Index: 290770 (The Pile)

Max Activating Token Index: 181

Text #8

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2705. Min Act: -0.0000

Data Index: 431837 (The Pile)

Max Activating Token Index: 69

Text #9

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2757. Min Act: -0.0000

Data Index: 604588 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2668. Min Act: -0.0000

Data Index: 865755 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1823384 (The Pile)

Max Activating Token Index: 612

Text #12

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1718173 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1731496 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2697. Min Act: -0.0000

Data Index: 168190 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1031002 (The Pile)

Max Activating Token Index: 17

Text #16

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2567. Min Act: -0.0000

Data Index: 1997898 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1985406 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2541. Min Act: -0.0000

Data Index: 891145 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 0.3760. Min Range: -0.3760

Max Act: 0.2433. Min Act: -0.0000

Data Index: 797787 (The Pile)

Max Activating Token Index: 165