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

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

Neuron 1365 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3659. Min Act: -0.0001

Data Index: 767106 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3311. Min Act: -0.0001

Data Index: 124509 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3292. Min Act: -0.0001

Data Index: 1161157 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2871. Min Act: -0.0001

Data Index: 332305 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1273134 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2649. Min Act: -0.0001

Data Index: 1285544 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2534. Min Act: -0.0001

Data Index: 532505 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1011363 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2266. Min Act: -0.0001

Data Index: 576430 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2499. Min Act: -0.0001

Data Index: 252942 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2313. Min Act: -0.0001

Data Index: 378125 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2456. Min Act: -0.0001

Data Index: 1505841 (Python Code)

Max Activating Token Index: 848

Text #12

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2300. Min Act: -0.0001

Data Index: 91417 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2193. Min Act: -0.0001

Data Index: 492470 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2398. Min Act: -0.0001

Data Index: 755593 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2206. Min Act: -0.0001

Data Index: 89653 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2306. Min Act: -0.0001

Data Index: 480039 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2125. Min Act: -0.0001

Data Index: 700016 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2181. Min Act: -0.0001

Data Index: 147234 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.3659. Min Range: -0.3659

Max Act: 0.2085. Min Act: -0.0001

Data Index: 601719 (C4 (Web Text))

Max Activating Token Index: 446