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

Dataset: The Pile

Neuron 545 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: 1.3035. Min Range: -1.3035

Max Act: 1.3035. Min Act: -0.0000

Data Index: 837329 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.2976. Min Act: -0.0000

Data Index: 673658 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1341625 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.2396. Min Act: -0.0000

Data Index: 736366 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1617. Min Act: -0.0000

Data Index: 3788 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1744. Min Act: -0.0000

Data Index: 1491704 (The Pile)

Max Activating Token Index: 859

Text #6

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1461. Min Act: -0.0000

Data Index: 1168531 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1760712 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1079521 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.0640. Min Act: -0.0000

Data Index: 1669027 (The Pile)

Max Activating Token Index: 467

Text #10

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1534. Min Act: -0.0000

Data Index: 136698 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1082. Min Act: -0.0000

Data Index: 1738531 (The Pile)

Max Activating Token Index: 630

Text #12

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1336. Min Act: -0.0000

Data Index: 919932 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.2319. Min Act: -0.0000

Data Index: 996359 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1390. Min Act: -0.0000

Data Index: 514500 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1434. Min Act: -0.0000

Data Index: 218242 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1702918 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1419822 (The Pile)

Max Activating Token Index: 779

Text #18

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1405258 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 1.3035. Min Range: -1.3035

Max Act: 1.1427. Min Act: -0.0000

Data Index: 850047 (The Pile)

Max Activating Token Index: 186