Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3973 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1102867 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0934. Min Act: -0.0001

Data Index: 975755 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0860. Min Act: -0.0001

Data Index: 546223 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1559457 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1093554 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0785. Min Act: -0.0001

Data Index: 52142 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0761. Min Act: -0.0001

Data Index: 535894 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1532701 (Python Code)

Max Activating Token Index: 363

Text #8

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0735. Min Act: -0.0001

Data Index: 356619 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0702. Min Act: -0.0001

Data Index: 74089 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0718. Min Act: -0.0001

Data Index: 987486 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0744. Min Act: -0.0001

Data Index: 1053703 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0741. Min Act: -0.0001

Data Index: 940300 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0703. Min Act: -0.0001

Data Index: 923108 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0727. Min Act: -0.0001

Data Index: 284043 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0714. Min Act: -0.0001

Data Index: 857179 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1151190 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0679. Min Act: -0.0001

Data Index: 900678 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1294117 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1235342 (C4 (Web Text))

Max Activating Token Index: 163