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

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

Neuron 3624 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0702. Min Act: -0.0001

Data Index: 329237 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1101264 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0650. Min Act: -0.0001

Data Index: 189737 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0731. Min Act: -0.0001

Data Index: 164844 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0653. Min Act: -0.0001

Data Index: 124638 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0683. Min Act: -0.0001

Data Index: 634623 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1132816 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0653. Min Act: -0.0001

Data Index: 28057 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0652. Min Act: -0.0001

Data Index: 478827 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0673. Min Act: -0.0001

Data Index: 634326 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0641. Min Act: -0.0001

Data Index: 99663 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0639. Min Act: -0.0001

Data Index: 477832 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0623. Min Act: -0.0001

Data Index: 44988 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1140054 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0620. Min Act: -0.0001

Data Index: 581320 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0680. Min Act: -0.0001

Data Index: 539530 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1019022 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0656. Min Act: -0.0001

Data Index: 342628 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0632. Min Act: -0.0001

Data Index: 933641 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.0731. Min Range: -0.0731

Max Act: 0.0611. Min Act: -0.0001

Data Index: 218698 (C4 (Web Text))

Max Activating Token Index: 686