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

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

Neuron 2936 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: 1.7813. Min Range: -1.7813

Max Act: 1.7746. Min Act: -0.0001

Data Index: 1290306 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.7813. Min Act: -0.0001

Data Index: 601589 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.7544. Min Act: -0.0001

Data Index: 970959 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.6315. Min Act: -0.0001

Data Index: 1103131 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.4960. Min Act: -0.0001

Data Index: 433530 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.5169. Min Act: -0.0001

Data Index: 123819 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.4944. Min Act: -0.0001

Data Index: 1206097 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.4864. Min Act: -0.0001

Data Index: 369830 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.5233. Min Act: -0.0001

Data Index: 880827 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.5704. Min Act: -0.0001

Data Index: 565331 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.3831. Min Act: -0.0001

Data Index: 112543 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.4493. Min Act: -0.0001

Data Index: 423188 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.4892. Min Act: -0.0001

Data Index: 1298936 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.4005. Min Act: -0.0001

Data Index: 1132902 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.2899. Min Act: -0.0001

Data Index: 1028666 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.3843. Min Act: -0.0001

Data Index: 900241 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.3490. Min Act: -0.0001

Data Index: 125522 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.3880. Min Act: -0.0001

Data Index: 1066041 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.3184. Min Act: -0.0001

Data Index: 210870 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 1.7813. Min Range: -1.7813

Max Act: 1.3394. Min Act: -0.0001

Data Index: 1084715 (C4 (Web Text))

Max Activating Token Index: 355