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

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

Neuron 2770 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.2364. Min Act: -0.0000

Data Index: 419395 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.2306. Min Act: -0.0000

Data Index: 1471 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1121296 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 1.2364. Min Range: -1.2364

Max Act: 1.0616. Min Act: -0.0000

Data Index: 154896 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.9990. Min Act: -0.0000

Data Index: 818459 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1280801 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8575. Min Act: 0.0000

Data Index: 624036 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8558. Min Act: 0.0000

Data Index: 156032 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8926. Min Act: 0.0000

Data Index: 720053 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8751. Min Act: 0.0000

Data Index: 622371 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8677. Min Act: -0.0000

Data Index: 472263 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1240700 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8605. Min Act: 0.0000

Data Index: 921852 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8572. Min Act: -0.0000

Data Index: 199453 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8572. Min Act: -0.0000

Data Index: 942908 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8328. Min Act: -0.0000

Data Index: 81515 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8242. Min Act: -0.0000

Data Index: 362914 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8119. Min Act: -0.0000

Data Index: 344302 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1053767 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.2364. Min Range: -1.2364

Max Act: 0.8071. Min Act: -0.0000

Data Index: 375674 (C4 (Web Text))

Max Activating Token Index: 126