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

Dataset: The Pile

Neuron 3494 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: 1.1786. Min Range: -1.1786

Max Act: 1.1786. Min Act: -0.0000

Data Index: 428122 (The Pile)

Max Activating Token Index: 783

Text #1

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9771. Min Act: -0.0000

Data Index: 40869 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1112799 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9615. Min Act: -0.0000

Data Index: 1152663 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9216. Min Act: -0.0000

Data Index: 164344 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9215. Min Act: 0.0000

Data Index: 1232273 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1525598 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8851. Min Act: -0.0000

Data Index: 322278 (The Pile)

Max Activating Token Index: 597

Text #8

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1770509 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1558426 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8696. Min Act: -0.0000

Data Index: 1772750 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9166. Min Act: -0.0000

Data Index: 820009 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1536759 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1427627 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1266870 (The Pile)

Max Activating Token Index: 993

Text #15

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1663459 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1863295 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1079454 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1733086 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1934986 (The Pile)

Max Activating Token Index: 33