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

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

Neuron 894 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1338. Min Range: -1.1338

Max Act: 1.1338. Min Act: -0.0001

Data Index: 378616 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 1.1338. Min Range: -1.1338

Max Act: 1.0839. Min Act: -0.0001

Data Index: 1218916 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9628. Min Act: -0.0001

Data Index: 1231846 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9408. Min Act: -0.0001

Data Index: 1205829 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9045. Min Act: -0.0001

Data Index: 1197936 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8264. Min Act: -0.0001

Data Index: 455810 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8535. Min Act: -0.0001

Data Index: 483496 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.9173. Min Act: -0.0001

Data Index: 93712 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.7897. Min Act: -0.0001

Data Index: 381298 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8597. Min Act: -0.0001

Data Index: 131179 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.8739. Min Act: -0.0001

Data Index: 780671 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.7503. Min Act: -0.0001

Data Index: 995826 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.7465. Min Act: -0.0001

Data Index: 990563 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.7401. Min Act: -0.0001

Data Index: 274908 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.7718. Min Act: -0.0001

Data Index: 987592 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.7331. Min Act: -0.0001

Data Index: 43367 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.6868. Min Act: -0.0001

Data Index: 742954 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.7284. Min Act: -0.0001

Data Index: 219398 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.7406. Min Act: -0.0001

Data Index: 472034 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.1338. Min Range: -1.1338

Max Act: 0.7569. Min Act: -0.0001

Data Index: 561777 (C4 (Web Text))

Max Activating Token Index: 984