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

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

Neuron 4014 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1341385 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1063764 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1040331 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1148390 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1235482 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1338696 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4466. Min Act: -0.0000

Data Index: 521432 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4578. Min Act: -0.0000

Data Index: 982311 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4238. Min Act: -0.0000

Data Index: 766171 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.5801. Min Act: -0.0000

Data Index: 684736 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4309. Min Act: -0.0000

Data Index: 58041 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4296. Min Act: -0.0000

Data Index: 918204 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4114. Min Act: -0.0000

Data Index: 626000 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4196. Min Act: -0.0000

Data Index: 317258 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4110. Min Act: -0.0000

Data Index: 162601 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3941. Min Act: -0.0000

Data Index: 241388 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3984. Min Act: -0.0000

Data Index: 768858 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1119759 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.3980. Min Act: -0.0000

Data Index: 912579 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.7300. Min Range: -0.7300

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1261441 (C4 (Web Text))

Max Activating Token Index: 906