Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2571 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6599. Min Act: -0.0000

Data Index: 1694102 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6337. Min Act: -0.0000

Data Index: 980653 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5264. Min Act: -0.0000

Data Index: 1434528 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1253144 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1596272 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4917. Min Act: -0.0000

Data Index: 812599 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5105. Min Act: -0.0000

Data Index: 531947 (The Pile)

Max Activating Token Index: 390

Text #7

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5117. Min Act: -0.0001

Data Index: 1384 (The Pile)

Max Activating Token Index: 296

Text #8

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1023837 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4587. Min Act: -0.0001

Data Index: 1638171 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4463. Min Act: -0.0000

Data Index: 379837 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1357928 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.3934. Min Act: -0.0000

Data Index: 530785 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1113474 (The Pile)

Max Activating Token Index: 412

Text #14

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1630380 (The Pile)

Max Activating Token Index: 723

Text #15

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1316506 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1105853 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1434614 (The Pile)

Max Activating Token Index: 657

Text #18

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1591942 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4474. Min Act: -0.0000

Data Index: 713737 (The Pile)

Max Activating Token Index: 581