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

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

Neuron 1874 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.5366. Min Act: -0.0000

Data Index: 729820 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1005674 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4626. Min Act: -0.0000

Data Index: 98180 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4780. Min Act: -0.0000

Data Index: 762515 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4928. Min Act: -0.0000

Data Index: 324431 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4616. Min Act: -0.0000

Data Index: 440839 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4106. Min Act: -0.0000

Data Index: 668422 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4471. Min Act: -0.0000

Data Index: 875788 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1289064 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3863. Min Act: -0.0001

Data Index: 923278 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1131829 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1311189 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1009225 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3702. Min Act: -0.0001

Data Index: 440550 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3704. Min Act: -0.0001

Data Index: 1134465 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3593. Min Act: -0.0001

Data Index: 874723 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3504. Min Act: -0.0000

Data Index: 883010 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1053743 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3436. Min Act: -0.0000

Data Index: 349745 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.5628. Min Range: -0.5628

Max Act: 0.3194. Min Act: -0.0000

Data Index: 580495 (C4 (Web Text))

Max Activating Token Index: 801