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

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

Neuron 4916 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: 0.3358. Min Range: -0.3358

Max Act: 0.3358. Min Act: -0.0000

Data Index: 52970 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3038. Min Act: -0.0000

Data Index: 280986 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1166738 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2948. Min Act: -0.0000

Data Index: 400514 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2911. Min Act: -0.0000

Data Index: 1075151 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2858. Min Act: 0.0001

Data Index: 906449 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2872. Min Act: -0.0000

Data Index: 924104 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2968. Min Act: -0.0000

Data Index: 443840 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2759. Min Act: -0.0000

Data Index: 245053 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2813. Min Act: -0.0000

Data Index: 734696 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2694. Min Act: -0.0000

Data Index: 596165 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2786. Min Act: -0.0000

Data Index: 328756 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2679. Min Act: -0.0000

Data Index: 801093 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2751. Min Act: -0.0000

Data Index: 923577 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2674. Min Act: -0.0000

Data Index: 88124 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2771. Min Act: -0.0000

Data Index: 486028 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2564. Min Act: 0.0001

Data Index: 1248244 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2564. Min Act: -0.0000

Data Index: 257473 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1131420 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2649. Min Act: -0.0000

Data Index: 316060 (C4 (Web Text))

Max Activating Token Index: 140