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

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

Neuron 4277 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7251. Min Range: -2.7251

Max Act: 2.7251. Min Act: 0.0000

Data Index: 701274 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 2.7251. Min Range: -2.7251

Max Act: 2.5909. Min Act: -0.0000

Data Index: 1080483 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 2.7251. Min Range: -2.7251

Max Act: 2.4520. Min Act: 0.0000

Data Index: 18259 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 2.7251. Min Range: -2.7251

Max Act: 2.3574. Min Act: -0.0000

Data Index: 406201 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 2.7251. Min Range: -2.7251

Max Act: 2.1229. Min Act: 0.0000

Data Index: 1214074 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 2.7251. Min Range: -2.7251

Max Act: 2.1215. Min Act: -0.0000

Data Index: 1158265 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.9719. Min Act: -0.0000

Data Index: 668796 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.9748. Min Act: -0.0000

Data Index: 1081141 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.9388. Min Act: -0.0000

Data Index: 495212 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.9172. Min Act: -0.0000

Data Index: 425743 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.8000. Min Act: -0.0000

Data Index: 1250292 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.9992. Min Act: -0.0000

Data Index: 473667 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.7912. Min Act: -0.0000

Data Index: 939486 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.7715. Min Act: -0.0000

Data Index: 1167514 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.7326. Min Act: -0.0000

Data Index: 1531221 (Python Code)

Max Activating Token Index: 829

Text #15

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.6595. Min Act: -0.0000

Data Index: 1229103 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.6333. Min Act: -0.0000

Data Index: 1195374 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.5390. Min Act: -0.0000

Data Index: 194082 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.6394. Min Act: -0.0000

Data Index: 824999 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 2.7251. Min Range: -2.7251

Max Act: 1.5922. Min Act: -0.0000

Data Index: 421789 (C4 (Web Text))

Max Activating Token Index: 297