Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4548 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7579. Min Act: -0.0000

Data Index: 527339 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1116455 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1128169 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.8064. Min Act: -0.0000

Data Index: 583312 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.6992. Min Act: -0.0000

Data Index: 468303 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7281. Min Act: -0.0000

Data Index: 764376 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7040. Min Act: -0.0000

Data Index: 925119 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1006870 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.6295. Min Act: -0.0000

Data Index: 213643 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.6331. Min Act: -0.0000

Data Index: 912787 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.5697. Min Act: -0.0000

Data Index: 509076 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.5959. Min Act: -0.0000

Data Index: 788660 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.5352. Min Act: -0.0000

Data Index: 271105 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.4967. Min Act: -0.0000

Data Index: 810945 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.4567. Min Act: -0.0000

Data Index: 734812 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.4541. Min Act: -0.0000

Data Index: 800808 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.4649. Min Act: -0.0000

Data Index: 801013 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.4697. Min Act: -0.0000

Data Index: 225349 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.4002. Min Act: -0.0000

Data Index: 404163 (C4 (Web Text))

Max Activating Token Index: 140

Text #19

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1423226 (Python Code)

Max Activating Token Index: 416