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

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

Neuron 3234 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: 0.8629. Min Range: -0.8629

Max Act: 0.8629. Min Act: -0.0001

Data Index: 1446422 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7741. Min Act: -0.0001

Data Index: 667659 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6980. Min Act: -0.0001

Data Index: 385529 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6408. Min Act: -0.0001

Data Index: 1346506 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6664. Min Act: -0.0001

Data Index: 519065 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5947. Min Act: -0.0001

Data Index: 697577 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5872. Min Act: -0.0001

Data Index: 547199 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5771. Min Act: -0.0001

Data Index: 501699 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5925. Min Act: -0.0001

Data Index: 472269 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6024. Min Act: -0.0001

Data Index: 80678 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5824. Min Act: -0.0001

Data Index: 40932 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5902. Min Act: -0.0001

Data Index: 725220 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5605. Min Act: -0.0001

Data Index: 1035618 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5439. Min Act: -0.0001

Data Index: 1084142 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5395. Min Act: -0.0001

Data Index: 281534 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.4849. Min Act: -0.0001

Data Index: 446868 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5766. Min Act: -0.0001

Data Index: 739863 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5435. Min Act: -0.0001

Data Index: 142020 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5401. Min Act: -0.0001

Data Index: 288227 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5582. Min Act: -0.0001

Data Index: 119588 (C4 (Web Text))

Max Activating Token Index: 360