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

Dataset: The Pile

Neuron 2662 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1395060 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.5239. Min Act: -0.0000

Data Index: 337146 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1656927 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.4786. Min Act: -0.0000

Data Index: 668118 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1479077 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1993545 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.4904. Min Act: -0.0000

Data Index: 888078 (The Pile)

Max Activating Token Index: 459

Text #7

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.4663. Min Act: -0.0000

Data Index: 572523 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1543977 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1496041 (The Pile)

Max Activating Token Index: 112

Text #10

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3094. Min Act: -0.0000

Data Index: 940234 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3758. Min Act: -0.0000

Data Index: 393714 (The Pile)

Max Activating Token Index: 684

Text #12

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3469. Min Act: -0.0000

Data Index: 265134 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1686465 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3259. Min Act: -0.0000

Data Index: 391918 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3725. Min Act: -0.0000

Data Index: 406562 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1064714 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3814. Min Act: -0.0000

Data Index: 564724 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3202. Min Act: -0.0000

Data Index: 7646 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 0.8177. Min Range: -0.8177

Max Act: 0.3407. Min Act: -0.0000

Data Index: 163954 (The Pile)

Max Activating Token Index: 928