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

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

Neuron 1274 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.5110. Min Act: -0.0000

Data Index: 911651 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.1481. Min Act: -0.0000

Data Index: 447255 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.0383. Min Act: -0.0000

Data Index: 65859 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.0387. Min Act: -0.0000

Data Index: 354623 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 1.5110. Min Range: -1.5110

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1299891 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1297472 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1066278 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.9481. Min Act: -0.0000

Data Index: 991700 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.9637. Min Act: -0.0000

Data Index: 969747 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.9178. Min Act: -0.0000

Data Index: 493592 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.8853. Min Act: -0.0000

Data Index: 841443 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1081615 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1079466 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.9006. Min Act: -0.0000

Data Index: 321469 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.8556. Min Act: -0.0000

Data Index: 798715 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1164184 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.8595. Min Act: -0.0000

Data Index: 806351 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.8284. Min Act: -0.0000

Data Index: 1295403 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1320634 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 1.5110. Min Range: -1.5110

Max Act: 0.8166. Min Act: -0.0000

Data Index: 196478 (C4 (Web Text))

Max Activating Token Index: 500