Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 327 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2328. Min Act: -0.0003

Data Index: 220267 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2318. Min Act: -0.0003

Data Index: 516688 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2310. Min Act: -0.0003

Data Index: 745693 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2311. Min Act: -0.0003

Data Index: 235558 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2303. Min Act: -0.0003

Data Index: 57548 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2291. Min Act: -0.0003

Data Index: 1314496 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2289. Min Act: -0.0003

Data Index: 818410 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2284. Min Act: -0.0003

Data Index: 776497 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2277. Min Act: -0.0003

Data Index: 118039 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2277. Min Act: -0.0003

Data Index: 463070 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2193. Min Act: -0.0003

Data Index: 842992 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2276. Min Act: -0.0003

Data Index: 956482 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2187. Min Act: -0.0003

Data Index: 620271 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2272. Min Act: -0.0003

Data Index: 1213682 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2352. Min Act: -0.0003

Data Index: 774937 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2269. Min Act: -0.0003

Data Index: 976570 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2269. Min Act: -0.0003

Data Index: 1326507 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2270. Min Act: -0.0003

Data Index: 641604 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2182. Min Act: -0.0003

Data Index: 427743 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2263. Min Act: -0.0003

Data Index: 1181591 (C4 (Web Text))

Max Activating Token Index: 48