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

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

Neuron 1262 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: 0.0845. Min Range: -0.0845

Max Act: 0.0845. Min Act: -0.0001

Data Index: 388877 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1085388 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0776. Min Act: -0.0001

Data Index: 1276790 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0735. Min Act: -0.0001

Data Index: 59535 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0738. Min Act: -0.0001

Data Index: 473023 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1420931 (Python Code)

Max Activating Token Index: 718

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0586. Min Act: -0.0001

Data Index: 601297 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0627. Min Act: -0.0001

Data Index: 910422 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0617. Min Act: -0.0001

Data Index: 816349 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0634. Min Act: -0.0001

Data Index: 337691 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0630. Min Act: -0.0001

Data Index: 615355 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0586. Min Act: -0.0001

Data Index: 148221 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0618. Min Act: -0.0001

Data Index: 860156 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0582. Min Act: -0.0001

Data Index: 200380 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0609. Min Act: -0.0001

Data Index: 430021 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0572. Min Act: -0.0001

Data Index: 88674 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1459848 (Python Code)

Max Activating Token Index: 765

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0589. Min Act: -0.0001

Data Index: 959274 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0539. Min Act: -0.0001

Data Index: 317716 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1405914 (Python Code)

Max Activating Token Index: 540