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

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

Neuron 2537 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: 0.3294. Min Range: -0.3294

Max Act: 0.3294. Min Act: -0.0001

Data Index: 953822 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3060. Min Act: -0.0001

Data Index: 1096357 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2959. Min Act: -0.0001

Data Index: 723637 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3041. Min Act: -0.0001

Data Index: 1314206 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3103. Min Act: -0.0001

Data Index: 596581 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3014. Min Act: -0.0001

Data Index: 419702 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2864. Min Act: -0.0001

Data Index: 570281 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2972. Min Act: -0.0001

Data Index: 595669 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2960. Min Act: -0.0001

Data Index: 1089235 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2857. Min Act: -0.0001

Data Index: 1060063 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.3046. Min Act: -0.0001

Data Index: 664586 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2973. Min Act: -0.0001

Data Index: 30416 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2654. Min Act: -0.0001

Data Index: 248286 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2865. Min Act: -0.0001

Data Index: 906662 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1272133 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2645. Min Act: -0.0001

Data Index: 540154 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2723. Min Act: -0.0001

Data Index: 127336 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2707. Min Act: -0.0001

Data Index: 294843 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2661. Min Act: -0.0001

Data Index: 500587 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.3294. Min Range: -0.3294

Max Act: 0.2620. Min Act: -0.0001

Data Index: 15594 (C4 (Web Text))

Max Activating Token Index: 520