Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3962 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.3598. Min Act: -0.0001

Data Index: 824471 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.4257. Min Act: -0.0002

Data Index: 662087 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.4167. Min Act: -0.0002

Data Index: 215518 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.3798. Min Act: -0.0002

Data Index: 771475 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.2985. Min Act: -0.0002

Data Index: 919468 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.2476. Min Act: -0.0001

Data Index: 1620890 (Python Code)

Max Activating Token Index: 731

Text #6

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.3137. Min Act: -0.0001

Data Index: 283383 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.2338. Min Act: -0.0001

Data Index: 1625005 (Python Code)

Max Activating Token Index: 866

Text #8

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.3278. Min Act: -0.0001

Data Index: 464999 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.3538. Min Act: -0.0002

Data Index: 432790 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.0458. Min Act: -0.0001

Data Index: 81863 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.2434. Min Act: -0.0001

Data Index: 664097 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1151. Min Act: -0.0001

Data Index: 1573171 (Python Code)

Max Activating Token Index: 945

Text #13

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1481. Min Act: -0.0002

Data Index: 818470 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1038. Min Act: -0.0002

Data Index: 950545 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1945. Min Act: -0.0001

Data Index: 557359 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1009. Min Act: -0.0001

Data Index: 931376 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1473. Min Act: -0.0001

Data Index: 211133 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.3405. Min Act: -0.0001

Data Index: 300150 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 1.4257. Min Range: -1.4257

Max Act: 1.1601. Min Act: -0.0001

Data Index: 186453 (C4 (Web Text))

Max Activating Token Index: 478