Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 183 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2360. Min Act: -0.0001

Data Index: 854985 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1262967 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2212. Min Act: -0.0001

Data Index: 1591646 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2370. Min Act: -0.0001

Data Index: 15958 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1640137 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2194. Min Act: -0.0001

Data Index: 943117 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2279. Min Act: -0.0000

Data Index: 575872 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2180. Min Act: -0.0001

Data Index: 1510340 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1094686 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2071. Min Act: -0.0001

Data Index: 490070 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2371. Min Act: -0.0000

Data Index: 135071 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2057. Min Act: -0.0001

Data Index: 246515 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1920. Min Act: -0.0001

Data Index: 40965 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1493546 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.2004. Min Act: -0.0001

Data Index: 85191 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1989. Min Act: -0.0001

Data Index: 1586082 (Python Code)

Max Activating Token Index: 1022

Text #16

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1850. Min Act: -0.0001

Data Index: 504156 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1985. Min Act: -0.0000

Data Index: 579549 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1087873 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 0.2371. Min Range: -0.2371

Max Act: 0.1981. Min Act: -0.0001

Data Index: 686266 (C4 (Web Text))

Max Activating Token Index: 452