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

Dataset: The Pile

Neuron 3524 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.7977. Min Act: -0.0000

Data Index: 984856 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1757420 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1612647 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1772677 (The Pile)

Max Activating Token Index: 245

Text #4

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.7589. Min Act: -0.0000

Data Index: 130200 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1549557 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6880. Min Act: -0.0000

Data Index: 15469 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.7045. Min Act: -0.0000

Data Index: 347560 (The Pile)

Max Activating Token Index: 505

Text #8

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6964. Min Act: -0.0000

Data Index: 462918 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6587. Min Act: -0.0000

Data Index: 8665 (The Pile)

Max Activating Token Index: 390

Text #10

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6550. Min Act: -0.0000

Data Index: 349062 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6920. Min Act: -0.0000

Data Index: 556549 (The Pile)

Max Activating Token Index: 277

Text #12

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6843. Min Act: -0.0000

Data Index: 208452 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1452386 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1837013 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6697. Min Act: -0.0000

Data Index: 98922 (The Pile)

Max Activating Token Index: 463

Text #16

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1875991 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1694106 (The Pile)

Max Activating Token Index: 773

Text #18

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1028434 (The Pile)

Max Activating Token Index: 798

Text #19

Max Range: 0.8150. Min Range: -0.8150

Max Act: 0.6720. Min Act: -0.0000

Data Index: 715294 (The Pile)

Max Activating Token Index: 383