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

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

Neuron 586 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: 644518 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1081104 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0674. Min Act: -0.0001

Data Index: 208069 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0690. Min Act: -0.0001

Data Index: 828239 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0603. Min Act: -0.0001

Data Index: 793767 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0614. Min Act: -0.0001

Data Index: 369453 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0598. Min Act: -0.0001

Data Index: 236443 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0578. Min Act: -0.0001

Data Index: 315642 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0575. Min Act: -0.0001

Data Index: 400730 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1177022 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1249571 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0562. Min Act: -0.0001

Data Index: 112315 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0524. Min Act: -0.0001

Data Index: 463900 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0532. Min Act: -0.0001

Data Index: 442096 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1007923 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1305953 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1354420 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0515. Min Act: -0.0001

Data Index: 814402 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1195665 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0845. Min Range: -0.0845

Max Act: 0.0471. Min Act: -0.0001

Data Index: 127506 (C4 (Web Text))

Max Activating Token Index: 241