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

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

Neuron 3974 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.5956. Min Act: -0.0000

Data Index: 78024 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.4850. Min Act: -0.0000

Data Index: 1099254 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.3667. Min Act: -0.0000

Data Index: 35322 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.4461. Min Act: -0.0000

Data Index: 1072425 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.2970. Min Act: -0.0000

Data Index: 1529226 (Python Code)

Max Activating Token Index: 109

Text #5

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1390420 (Python Code)

Max Activating Token Index: 635

Text #6

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.4192. Min Act: -0.0000

Data Index: 898443 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.3413. Min Act: -0.0000

Data Index: 85653 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.3565. Min Act: -0.0000

Data Index: 1385098 (Python Code)

Max Activating Token Index: 919

Text #9

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.1898. Min Act: -0.0000

Data Index: 444562 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.4225. Min Act: -0.0000

Data Index: 1057423 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.2270. Min Act: -0.0000

Data Index: 1320780 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.3199. Min Act: -0.0000

Data Index: 86065 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.3152. Min Act: -0.0000

Data Index: 1318675 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.4052. Min Act: -0.0000

Data Index: 605925 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.3235. Min Act: -0.0000

Data Index: 811849 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.2757. Min Act: -0.0000

Data Index: 1432159 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.3878. Min Act: -0.0000

Data Index: 1474588 (Python Code)

Max Activating Token Index: 215

Text #18

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.2569. Min Act: -0.0000

Data Index: 962423 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.5956. Min Range: -1.5956

Max Act: 1.3019. Min Act: -0.0000

Data Index: 972555 (C4 (Web Text))

Max Activating Token Index: 68