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

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

Neuron 1843 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: 0.2757. Min Range: -0.2757

Max Act: 0.2757. Min Act: -0.0001

Data Index: 1104886 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2481. Min Act: -0.0001

Data Index: 499316 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2534. Min Act: -0.0001

Data Index: 421902 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2516. Min Act: -0.0001

Data Index: 458137 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2271. Min Act: -0.0001

Data Index: 295347 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2272. Min Act: -0.0001

Data Index: 1155564 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2196. Min Act: -0.0001

Data Index: 245851 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2165. Min Act: -0.0001

Data Index: 626795 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2184. Min Act: -0.0001

Data Index: 242139 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2172. Min Act: -0.0001

Data Index: 71566 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1244127 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2206. Min Act: -0.0001

Data Index: 62826 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1021580 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2181. Min Act: -0.0001

Data Index: 1105974 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1941. Min Act: -0.0001

Data Index: 744894 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1000624 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2260. Min Act: -0.0001

Data Index: 1025136 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2274. Min Act: -0.0001

Data Index: 330729 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2265. Min Act: -0.0001

Data Index: 869265 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2175. Min Act: -0.0001

Data Index: 1171598 (C4 (Web Text))

Max Activating Token Index: 722