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

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

Neuron 619 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.6023. Min Act: -0.0000

Data Index: 1251940 (C4 (Web Text))

Max Activating Token Index: 290

Text #1

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.6845. Min Act: -0.0000

Data Index: 1279316 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.4549. Min Act: -0.0000

Data Index: 588257 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.4488. Min Act: -0.0000

Data Index: 416606 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1300337 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.4334. Min Act: -0.0000

Data Index: 666295 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.4163. Min Act: -0.0000

Data Index: 469229 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1085166 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.3632. Min Act: -0.0000

Data Index: 886101 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1222267 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.2885. Min Act: -0.0000

Data Index: 391264 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.2880. Min Act: -0.0000

Data Index: 1095676 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.2793. Min Act: -0.0000

Data Index: 1167768 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.2362. Min Act: -0.0000

Data Index: 1345744 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.2880. Min Act: -0.0000

Data Index: 140041 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.1406. Min Act: -0.0000

Data Index: 357078 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.1735. Min Act: -0.0000

Data Index: 735225 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.1995. Min Act: -0.0000

Data Index: 825162 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.1985. Min Act: -0.0000

Data Index: 55761 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.6845. Min Range: -1.6845

Max Act: 1.1646. Min Act: -0.0000

Data Index: 328380 (C4 (Web Text))

Max Activating Token Index: 51