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

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

Neuron 4857 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1168988 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3653. Min Act: -0.0000

Data Index: 22163 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3666. Min Act: -0.0000

Data Index: 209923 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3535. Min Act: -0.0000

Data Index: 965065 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3402. Min Act: -0.0000

Data Index: 29453 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3238. Min Act: -0.0000

Data Index: 748998 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3196. Min Act: -0.0000

Data Index: 648553 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.2932. Min Act: -0.0000

Data Index: 136688 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3143. Min Act: -0.0000

Data Index: 1353368 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3086. Min Act: -0.0000

Data Index: 823654 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1309113 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1179106 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3109. Min Act: -0.0000

Data Index: 574375 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.2909. Min Act: -0.0000

Data Index: 63515 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3025. Min Act: -0.0000

Data Index: 757378 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.2906. Min Act: -0.0000

Data Index: 737035 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1081064 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.2860. Min Act: -0.0000

Data Index: 357034 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.3128. Min Act: -0.0000

Data Index: 439824 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.4045. Min Range: -0.4045

Max Act: 0.2764. Min Act: -0.0000

Data Index: 779800 (C4 (Web Text))

Max Activating Token Index: 679