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

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

Neuron 4595 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: 2.9239. Min Range: -2.9239

Max Act: 2.9239. Min Act: -0.0000

Data Index: 1311338 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.7981. Min Act: -0.0000

Data Index: 201919 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.7998. Min Act: -0.0000

Data Index: 414909 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.6412. Min Act: -0.0000

Data Index: 1094180 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.7370. Min Act: -0.0000

Data Index: 1323928 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.8772. Min Act: -0.0000

Data Index: 623526 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.5787. Min Act: -0.0000

Data Index: 916743 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.4813. Min Act: -0.0000

Data Index: 757395 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.6009. Min Act: -0.0000

Data Index: 253280 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.5155. Min Act: -0.0000

Data Index: 898740 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.5176. Min Act: -0.0000

Data Index: 826077 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.3855. Min Act: -0.0000

Data Index: 1299462 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.4632. Min Act: -0.0000

Data Index: 1084227 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.4687. Min Act: -0.0000

Data Index: 1181031 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.3964. Min Act: -0.0000

Data Index: 718999 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.3805. Min Act: -0.0000

Data Index: 739553 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.2452. Min Act: -0.0000

Data Index: 1254233 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.3888. Min Act: -0.0000

Data Index: 2052 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.3653. Min Act: -0.0000

Data Index: 183907 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 2.9239. Min Range: -2.9239

Max Act: 2.3455. Min Act: -0.0000

Data Index: 6049 (C4 (Web Text))

Max Activating Token Index: 910