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

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

Neuron 1165 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1140640 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1116812 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1302284 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6409. Min Act: -0.0000

Data Index: 846137 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6884. Min Act: -0.0000

Data Index: 335523 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6444. Min Act: -0.0000

Data Index: 729147 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6222. Min Act: -0.0000

Data Index: 987720 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.5824. Min Act: -0.0000

Data Index: 246034 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6029. Min Act: -0.0000

Data Index: 414556 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6345. Min Act: -0.0000

Data Index: 821508 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1249363 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6062. Min Act: -0.0000

Data Index: 270347 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.5917. Min Act: -0.0000

Data Index: 294658 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1176903 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.5712. Min Act: -0.0000

Data Index: 510736 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.5809. Min Act: -0.0000

Data Index: 327516 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.6099. Min Act: -0.0000

Data Index: 359511 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.5952. Min Act: -0.0000

Data Index: 682220 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1216622 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.8037. Min Range: -0.8037

Max Act: 0.5482. Min Act: -0.0000

Data Index: 100395 (C4 (Web Text))

Max Activating Token Index: 265