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

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

Neuron 1420 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: 2.4151. Min Range: -2.4151

Max Act: 2.3038. Min Act: -0.0000

Data Index: 1524196 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.4151. Min Act: -0.0000

Data Index: 1181405 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.2270. Min Act: -0.0000

Data Index: 1582646 (Python Code)

Max Activating Token Index: 559

Text #3

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.2213. Min Act: -0.0000

Data Index: 1517865 (Python Code)

Max Activating Token Index: 627

Text #4

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.1029. Min Act: -0.0000

Data Index: 1399240 (Python Code)

Max Activating Token Index: 379

Text #5

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.2010. Min Act: -0.0000

Data Index: 1638536 (Python Code)

Max Activating Token Index: 917

Text #6

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.1751. Min Act: -0.0000

Data Index: 408269 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.1660. Min Act: -0.0000

Data Index: 576440 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.1453. Min Act: -0.0000

Data Index: 1473449 (Python Code)

Max Activating Token Index: 586

Text #9

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.1357. Min Act: -0.0000

Data Index: 961926 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.2411. Min Act: -0.0000

Data Index: 307934 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.0824. Min Act: -0.0000

Data Index: 387218 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.0461. Min Act: -0.0000

Data Index: 1365561 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.9405. Min Act: -0.0000

Data Index: 1281185 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.1350. Min Act: -0.0000

Data Index: 1469169 (Python Code)

Max Activating Token Index: 480

Text #15

Max Range: 2.4151. Min Range: -2.4151

Max Act: 2.0062. Min Act: -0.0000

Data Index: 1215454 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.9523. Min Act: -0.0000

Data Index: 218987 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.9398. Min Act: -0.0000

Data Index: 1015960 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.9163. Min Act: -0.0000

Data Index: 1647205 (Python Code)

Max Activating Token Index: 288

Text #19

Max Range: 2.4151. Min Range: -2.4151

Max Act: 1.7774. Min Act: -0.0000

Data Index: 107136 (C4 (Web Text))

Max Activating Token Index: 563