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

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

Neuron 3208 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.2363. Min Act: -0.0001

Data Index: 386605 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1815. Min Act: -0.0001

Data Index: 1063836 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1704. Min Act: -0.0001

Data Index: 1199749 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1448. Min Act: -0.0001

Data Index: 172695 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1573. Min Act: -0.0001

Data Index: 275405 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1896. Min Act: -0.0001

Data Index: 816036 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1354. Min Act: -0.0001

Data Index: 1150107 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9605. Min Act: -0.0001

Data Index: 541871 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.1275. Min Act: -0.0001

Data Index: 412499 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0156. Min Act: -0.0001

Data Index: 542457 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0143. Min Act: -0.0001

Data Index: 88738 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.9877. Min Act: -0.0001

Data Index: 785721 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 1.2363. Min Range: -1.2363

Max Act: 1.0033. Min Act: -0.0001

Data Index: 920150 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8244. Min Act: -0.0001

Data Index: 972832 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8226. Min Act: -0.0001

Data Index: 59482 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8055. Min Act: -0.0001

Data Index: 194254 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8040. Min Act: -0.0001

Data Index: 1214531 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8019. Min Act: -0.0001

Data Index: 443179 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.8839. Min Act: -0.0001

Data Index: 369193 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 1.2363. Min Range: -1.2363

Max Act: 0.7783. Min Act: -0.0001

Data Index: 771550 (C4 (Web Text))

Max Activating Token Index: 1018