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

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

Neuron 1042 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: 1.8920. Min Range: -1.8920

Max Act: 1.8920. Min Act: -0.0000

Data Index: 900667 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1013166 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.8511. Min Act: -0.0000

Data Index: 360567 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7406. Min Act: -0.0000

Data Index: 1129268 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7507. Min Act: -0.0000

Data Index: 460577 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.6996. Min Act: -0.0000

Data Index: 930014 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.8816. Min Act: -0.0000

Data Index: 638094 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7921. Min Act: -0.0000

Data Index: 728337 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7849. Min Act: -0.0000

Data Index: 716463 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7750. Min Act: -0.0000

Data Index: 711702 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7710. Min Act: -0.0000

Data Index: 363205 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.6028. Min Act: -0.0000

Data Index: 4897 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.8772. Min Act: -0.0000

Data Index: 97404 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.6275. Min Act: -0.0000

Data Index: 25069 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.6393. Min Act: -0.0000

Data Index: 826018 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.6121. Min Act: -0.0000

Data Index: 1242140 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7045. Min Act: -0.0000

Data Index: 1140579 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.6983. Min Act: -0.0000

Data Index: 1075520 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.6102. Min Act: -0.0000

Data Index: 41058 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 1.8920. Min Range: -1.8920

Max Act: 1.7951. Min Act: -0.0000

Data Index: 293154 (C4 (Web Text))

Max Activating Token Index: 919