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

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

Neuron 4225 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.9555. Min Act: 0.0001

Data Index: 89775 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.9086. Min Act: -0.0000

Data Index: 307959 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.9567. Min Act: -0.0000

Data Index: 1150048 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.8709. Min Act: -0.0000

Data Index: 1136775 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.7991. Min Act: -0.0000

Data Index: 1063888 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.6363. Min Act: -0.0000

Data Index: 1264867 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.7979. Min Act: 0.0001

Data Index: 1287940 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.8588. Min Act: -0.0000

Data Index: 882986 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.7949. Min Act: -0.0000

Data Index: 43278 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.7847. Min Act: -0.0000

Data Index: 641831 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.6644. Min Act: -0.0000

Data Index: 38776 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.7544. Min Act: -0.0000

Data Index: 1202565 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.6869. Min Act: -0.0000

Data Index: 949037 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.6435. Min Act: 0.0001

Data Index: 1255426 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.4829. Min Act: 0.0000

Data Index: 434474 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.6083. Min Act: -0.0000

Data Index: 684387 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.5400. Min Act: 0.0000

Data Index: 1169695 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.5796. Min Act: -0.0000

Data Index: 686856 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1043709 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 1.9567. Min Range: -1.9567

Max Act: 1.5951. Min Act: 0.0000

Data Index: 778404 (C4 (Web Text))

Max Activating Token Index: 865