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

Dataset: The Pile

Neuron 1910 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: 0.8010. Min Range: -0.8010

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1079728 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.8010. Min Act: -0.0000

Data Index: 849070 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1364299 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1908812 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1231923 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1272540 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1404683 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.6357. Min Act: -0.0000

Data Index: 709454 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1530658 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1654590 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1715985 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1739219 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1237442 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1031918 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5991. Min Act: -0.0000

Data Index: 875425 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5345. Min Act: -0.0000

Data Index: 848503 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5286. Min Act: -0.0000

Data Index: 844938 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5596. Min Act: -0.0000

Data Index: 873098 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5630. Min Act: -0.0000

Data Index: 893415 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 0.8010. Min Range: -0.8010

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1714677 (The Pile)

Max Activating Token Index: 523