Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6103 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1262345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2371. Min Act: -0.0001

Data Index: 936847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.0366. Min Act: -0.0001

Data Index: 438901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1873. Min Act: -0.0000

Data Index: 366491 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2182. Min Act: -0.0001

Data Index: 132387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1225. Min Act: -0.0001

Data Index: 12089 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1605502 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1292. Min Act: -0.0001

Data Index: 198060 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1279975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1495. Min Act: -0.0001

Data Index: 20138 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1004. Min Act: -0.0001

Data Index: 582132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1456. Min Act: -0.0000

Data Index: 310105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.0707. Min Act: -0.0001

Data Index: 523382 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1516286 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1305719 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.0580. Min Act: -0.0001

Data Index: 299720 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.0503. Min Act: -0.0000

Data Index: 374393 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.0468. Min Act: -0.0000

Data Index: 207645 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.0495. Min Act: -0.0000

Data Index: 901204 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.0296. Min Act: -0.0000

Data Index: 44232 (C4 (Web Text))

Max Activating Token Index: 1023