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

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

Neuron 1732 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3828. Min Act: -0.0001

Data Index: 967192 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3774. Min Act: -0.0001

Data Index: 1003342 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3547. Min Act: -0.0001

Data Index: 627603 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3641. Min Act: -0.0000

Data Index: 1228223 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3528. Min Act: -0.0000

Data Index: 660173 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3581. Min Act: -0.0000

Data Index: 706902 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3631. Min Act: -0.0001

Data Index: 286093 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3570. Min Act: -0.0001

Data Index: 823142 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3459. Min Act: -0.0000

Data Index: 856753 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3449. Min Act: -0.0000

Data Index: 616761 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1215746 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3433. Min Act: -0.0000

Data Index: 442346 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3358. Min Act: -0.0000

Data Index: 701833 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3402. Min Act: -0.0000

Data Index: 297360 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3274. Min Act: -0.0000

Data Index: 537415 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3363. Min Act: -0.0000

Data Index: 568608 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3360. Min Act: -0.0000

Data Index: 229915 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1268901 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3206. Min Act: -0.0000

Data Index: 489318 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3331. Min Act: -0.0000

Data Index: 755057 (C4 (Web Text))

Max Activating Token Index: 760