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

Dataset: The Pile

Neuron 860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.7290. Min Act: -0.0000

Data Index: 888165 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1377331 (The Pile)

Max Activating Token Index: 76

Text #2

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1598288 (The Pile)

Max Activating Token Index: 663

Text #3

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6255. Min Act: -0.0000

Data Index: 126173 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6042. Min Act: -0.0000

Data Index: 458051 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5929. Min Act: -0.0000

Data Index: 861710 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1642773 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6423. Min Act: -0.0000

Data Index: 10656 (The Pile)

Max Activating Token Index: 614

Text #8

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1389494 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1529146 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1780210 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5980. Min Act: -0.0000

Data Index: 823257 (The Pile)

Max Activating Token Index: 132

Text #12

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5678. Min Act: -0.0000

Data Index: 229617 (The Pile)

Max Activating Token Index: 756

Text #13

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5321. Min Act: -0.0000

Data Index: 918969 (The Pile)

Max Activating Token Index: 829

Text #14

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5641. Min Act: -0.0000

Data Index: 884931 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5731. Min Act: -0.0000

Data Index: 285716 (The Pile)

Max Activating Token Index: 34

Text #16

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5723. Min Act: -0.0000

Data Index: 606952 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1155610 (The Pile)

Max Activating Token Index: 889

Text #18

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5125. Min Act: -0.0000

Data Index: 809189 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1757084 (The Pile)

Max Activating Token Index: 75