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

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

Neuron 4436 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0402. Min Act: -0.0000

Data Index: 26645 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0376. Min Act: -0.0000

Data Index: 836296 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1322050 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0274. Min Act: -0.0000

Data Index: 980481 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0230. Min Act: 0.0000

Data Index: 331202 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0242. Min Act: -0.0000

Data Index: 30728 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0240. Min Act: -0.0000

Data Index: 93587 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0232. Min Act: -0.0000

Data Index: 1301965 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0231. Min Act: -0.0000

Data Index: 703542 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0230. Min Act: -0.0000

Data Index: 389538 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0217. Min Act: -0.0000

Data Index: 309686 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0217. Min Act: -0.0000

Data Index: 1644777 (Python Code)

Max Activating Token Index: 224

Text #12

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0224. Min Act: -0.0000

Data Index: 951690 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0220. Min Act: -0.0000

Data Index: 1114526 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0208. Min Act: -0.0000

Data Index: 868710 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0215. Min Act: -0.0000

Data Index: 34847 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0209. Min Act: -0.0000

Data Index: 384200 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0207. Min Act: -0.0000

Data Index: 785874 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0216. Min Act: -0.0000

Data Index: 699545 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.0402. Min Range: -0.0402

Max Act: 0.0207. Min Act: -0.0000

Data Index: 746697 (C4 (Web Text))

Max Activating Token Index: 686