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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2944 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.7986. Min Act: -0.0000

Data Index: 121972 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.6767. Min Act: -0.0001

Data Index: 284629 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.6957. Min Act: -0.0001

Data Index: 269237 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5469. Min Act: -0.0001

Data Index: 833437 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5793. Min Act: -0.0001

Data Index: 74206 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.6172. Min Act: -0.0001

Data Index: 335995 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5976. Min Act: -0.0000

Data Index: 156791 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.6707. Min Act: -0.0000

Data Index: 594883 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5240. Min Act: -0.0001

Data Index: 1340279 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5633. Min Act: -0.0001

Data Index: 473607 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1174544 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5023. Min Act: -0.0001

Data Index: 1048250 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5369. Min Act: -0.0001

Data Index: 714784 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.4486. Min Act: -0.0001

Data Index: 605160 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5424. Min Act: -0.0000

Data Index: 75192 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.4807. Min Act: -0.0001

Data Index: 1276744 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5415. Min Act: -0.0001

Data Index: 1013235 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.4427. Min Act: -0.0001

Data Index: 844382 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.5211. Min Act: -0.0001

Data Index: 215604 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 1.7986. Min Range: -1.7986

Max Act: 1.4725. Min Act: -0.0001

Data Index: 174730 (C4 (Web Text))

Max Activating Token Index: 647