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

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

Neuron 394 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.7205. Min Act: -0.0000

Data Index: 83046 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.5845. Min Act: -0.0000

Data Index: 827826 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.6257. Min Act: -0.0000

Data Index: 1210703 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1016756 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.4677. Min Act: -0.0000

Data Index: 117628 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3594. Min Act: -0.0000

Data Index: 953274 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1033899 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3642. Min Act: -0.0000

Data Index: 1000804 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3440. Min Act: -0.0000

Data Index: 1023718 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.3063. Min Act: -0.0000

Data Index: 424607 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2602. Min Act: -0.0000

Data Index: 773853 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2493. Min Act: -0.0000

Data Index: 1078725 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2665. Min Act: -0.0000

Data Index: 212755 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2266. Min Act: -0.0000

Data Index: 264378 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2571. Min Act: -0.0000

Data Index: 488718 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2092. Min Act: -0.0000

Data Index: 860685 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2089. Min Act: -0.0000

Data Index: 887168 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.1977. Min Act: -0.0000

Data Index: 444431 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2412. Min Act: -0.0000

Data Index: 385335 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.7205. Min Range: -1.7205

Max Act: 1.2270. Min Act: -0.0000

Data Index: 649941 (C4 (Web Text))

Max Activating Token Index: 291