Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3469 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2677. Min Act: -0.0002

Data Index: 692057 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2480. Min Act: -0.0002

Data Index: 1197451 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2285. Min Act: -0.0002

Data Index: 1227286 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2425. Min Act: -0.0002

Data Index: 744654 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2296. Min Act: -0.0002

Data Index: 660957 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2243. Min Act: -0.0002

Data Index: 244849 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2010. Min Act: -0.0002

Data Index: 33750 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2042. Min Act: -0.0002

Data Index: 1263100 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1968. Min Act: -0.0002

Data Index: 907467 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1894. Min Act: -0.0002

Data Index: 64504 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.2081. Min Act: -0.0002

Data Index: 500079 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1994. Min Act: -0.0002

Data Index: 658953 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1966. Min Act: -0.0002

Data Index: 1099438 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1890. Min Act: -0.0002

Data Index: 832400 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1892. Min Act: -0.0002

Data Index: 248339 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1855. Min Act: -0.0002

Data Index: 1073483 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1892. Min Act: -0.0002

Data Index: 402424 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1953. Min Act: -0.0002

Data Index: 753252 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1988. Min Act: -0.0002

Data Index: 1262316 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.2677. Min Range: -0.2677

Max Act: 0.1747. Min Act: -0.0002

Data Index: 324970 (C4 (Web Text))

Max Activating Token Index: 85