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

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

Neuron 5543 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.9047. Min Act: -0.0000

Data Index: 1315035 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7680. Min Act: -0.0000

Data Index: 147005 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.8628. Min Act: -0.0000

Data Index: 536960 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1338719 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7727. Min Act: -0.0000

Data Index: 341220 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1265384 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.6852. Min Act: -0.0000

Data Index: 911335 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1112932 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1177121 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.6133. Min Act: -0.0000

Data Index: 349031 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1343350 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5810. Min Act: -0.0000

Data Index: 607724 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5879. Min Act: -0.0000

Data Index: 780301 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5569. Min Act: -0.0000

Data Index: 346173 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5984. Min Act: -0.0000

Data Index: 270497 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5402. Min Act: -0.0000

Data Index: 1201090 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5516. Min Act: -0.0000

Data Index: 302424 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5284. Min Act: -0.0000

Data Index: 276610 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1624040 (Python Code)

Max Activating Token Index: 742

Text #19

Max Range: 0.9047. Min Range: -0.9047

Max Act: 0.5396. Min Act: -0.0000

Data Index: 907298 (C4 (Web Text))

Max Activating Token Index: 600