Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3709 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2621. Min Act: -0.0001

Data Index: 816327 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2785. Min Act: -0.0001

Data Index: 185499 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2578. Min Act: -0.0001

Data Index: 376415 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2313. Min Act: -0.0001

Data Index: 530495 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2521. Min Act: -0.0001

Data Index: 866707 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2369. Min Act: -0.0001

Data Index: 368337 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2453. Min Act: -0.0001

Data Index: 108756 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2482. Min Act: -0.0001

Data Index: 769076 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2235. Min Act: -0.0001

Data Index: 816914 (C4 (Web Text))

Max Activating Token Index: 599

Text #9

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1215482 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2310. Min Act: -0.0001

Data Index: 891286 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2404. Min Act: -0.0001

Data Index: 182689 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2309. Min Act: -0.0001

Data Index: 218463 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2211. Min Act: -0.0001

Data Index: 1242933 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2208. Min Act: -0.0001

Data Index: 79943 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2138. Min Act: -0.0001

Data Index: 710073 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2376. Min Act: -0.0001

Data Index: 217655 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2286. Min Act: -0.0001

Data Index: 443069 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2195. Min Act: -0.0001

Data Index: 675644 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2183. Min Act: -0.0001

Data Index: 1288426 (C4 (Web Text))

Max Activating Token Index: 647