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

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

Neuron 5393 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: 0.3607. Min Range: -0.3607

Max Act: 0.3449. Min Act: -0.0000

Data Index: 105922 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3607. Min Act: -0.0000

Data Index: 868553 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3451. Min Act: -0.0000

Data Index: 302779 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2933. Min Act: -0.0000

Data Index: 740744 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1258933 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1006620 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2847. Min Act: -0.0000

Data Index: 936346 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2617. Min Act: -0.0000

Data Index: 995119 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2840. Min Act: -0.0001

Data Index: 455837 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1180428 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1144839 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2752. Min Act: -0.0001

Data Index: 648025 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2800. Min Act: -0.0000

Data Index: 17148 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2799. Min Act: -0.0001

Data Index: 1346834 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2536. Min Act: -0.0000

Data Index: 475743 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2340. Min Act: -0.0001

Data Index: 1294656 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2755. Min Act: -0.0001

Data Index: 585661 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2558. Min Act: -0.0001

Data Index: 262594 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2407. Min Act: -0.0000

Data Index: 833895 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2354. Min Act: -0.0000

Data Index: 31279 (C4 (Web Text))

Max Activating Token Index: 82