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

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

Neuron 4250 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: 0.6041. Min Range: -0.6041

Max Act: 0.6036. Min Act: -0.0002

Data Index: 1125449 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5888. Min Act: -0.0002

Data Index: 1234666 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5346. Min Act: -0.0002

Data Index: 139447 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5762. Min Act: -0.0002

Data Index: 114680 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4964. Min Act: -0.0002

Data Index: 347585 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5214. Min Act: -0.0002

Data Index: 841406 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5072. Min Act: -0.0002

Data Index: 591498 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5800. Min Act: -0.0002

Data Index: 611762 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5698. Min Act: -0.0002

Data Index: 1025563 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4704. Min Act: -0.0002

Data Index: 639914 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5750. Min Act: -0.0002

Data Index: 373965 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5316. Min Act: -0.0002

Data Index: 308989 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4928. Min Act: -0.0002

Data Index: 991961 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4909. Min Act: -0.0002

Data Index: 197925 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4694. Min Act: -0.0002

Data Index: 305735 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5090. Min Act: -0.0002

Data Index: 99249 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4640. Min Act: -0.0002

Data Index: 325979 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.6041. Min Act: -0.0002

Data Index: 549525 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.5179. Min Act: -0.0002

Data Index: 418144 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.6041. Min Range: -0.6041

Max Act: 0.4731. Min Act: -0.0002

Data Index: 1356604 (C4 (Web Text))

Max Activating Token Index: 365