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

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

Neuron 3590 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.4957. Min Act: -0.0000

Data Index: 706775 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.4487. Min Act: -0.0001

Data Index: 298490 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.3358. Min Act: -0.0001

Data Index: 28894 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.2031. Min Act: -0.0001

Data Index: 1057677 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.3865. Min Act: -0.0001

Data Index: 587296 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.2349. Min Act: -0.0000

Data Index: 695697 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.2459. Min Act: -0.0001

Data Index: 610102 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.1863. Min Act: -0.0000

Data Index: 124571 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.2364. Min Act: -0.0000

Data Index: 749227 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.2001. Min Act: -0.0001

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.1982. Min Act: -0.0001

Data Index: 1260164 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.2169. Min Act: -0.0001

Data Index: 295299 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.1788. Min Act: -0.0000

Data Index: 1323611 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.0559. Min Act: -0.0001

Data Index: 871320 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1047523 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 1.4957. Min Range: -1.4957

Max Act: 0.9636. Min Act: -0.0001

Data Index: 1064515 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1040067 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.1022. Min Act: -0.0001

Data Index: 135314 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.1820. Min Act: -0.0001

Data Index: 501180 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 1.4957. Min Range: -1.4957

Max Act: 1.0516. Min Act: -0.0000

Data Index: 75088 (C4 (Web Text))

Max Activating Token Index: 516