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

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

Neuron 2407 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3462. Min Range: -3.3462

Max Act: 3.3462. Min Act: -0.0000

Data Index: 823569 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 3.3462. Min Range: -3.3462

Max Act: 3.0226. Min Act: -0.0000

Data Index: 997484 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 3.3462. Min Range: -3.3462

Max Act: 3.0032. Min Act: -0.0000

Data Index: 365935 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.8590. Min Act: -0.0000

Data Index: 878618 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.5902. Min Act: -0.0000

Data Index: 43675 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.3862. Min Act: -0.0000

Data Index: 1204002 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.3330. Min Act: -0.0000

Data Index: 675045 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.1910. Min Act: -0.0000

Data Index: 151166 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.2800. Min Act: -0.0000

Data Index: 1002599 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.0816. Min Act: -0.0000

Data Index: 93166 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.2998. Min Act: -0.0000

Data Index: 1197181 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.2285. Min Act: -0.0000

Data Index: 547954 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.0741. Min Act: -0.0000

Data Index: 1277455 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.0695. Min Act: -0.0000

Data Index: 616228 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 3.3462. Min Range: -3.3462

Max Act: 1.9376. Min Act: -0.0000

Data Index: 1148502 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.0203. Min Act: -0.0000

Data Index: 148562 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.2084. Min Act: -0.0000

Data Index: 334153 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 3.3462. Min Range: -3.3462

Max Act: 2.0835. Min Act: -0.0000

Data Index: 776261 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 3.3462. Min Range: -3.3462

Max Act: 1.8590. Min Act: -0.0000

Data Index: 715057 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.3462. Min Range: -3.3462

Max Act: 1.8871. Min Act: -0.0000

Data Index: 516292 (C4 (Web Text))

Max Activating Token Index: 645