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

Dataset: The Pile

Neuron 3286 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: 1.7742. Min Range: -1.7742

Max Act: 1.7742. Min Act: -0.0000

Data Index: 757955 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 1.7742. Min Range: -1.7742

Max Act: 1.7663. Min Act: -0.0000

Data Index: 1432928 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 1.7742. Min Range: -1.7742

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1958391 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 1.7742. Min Range: -1.7742

Max Act: 1.3524. Min Act: -0.0000

Data Index: 83872 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 1.7742. Min Range: -1.7742

Max Act: 1.3513. Min Act: -0.0000

Data Index: 1162406 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 1.7742. Min Range: -1.7742

Max Act: 1.1923. Min Act: -0.0000

Data Index: 1940491 (The Pile)

Max Activating Token Index: 945

Text #6

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1330760 (The Pile)

Max Activating Token Index: 947

Text #7

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.8615. Min Act: -0.0000

Data Index: 617886 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1174877 (The Pile)

Max Activating Token Index: 245

Text #9

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.8969. Min Act: -0.0000

Data Index: 403885 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1206353 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1577540 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1231488 (The Pile)

Max Activating Token Index: 564

Text #13

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1010574 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.8716. Min Act: -0.0000

Data Index: 665678 (The Pile)

Max Activating Token Index: 245

Text #15

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1628526 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.9503. Min Act: -0.0000

Data Index: 678597 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1631081 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1651055 (The Pile)

Max Activating Token Index: 689

Text #19

Max Range: 1.7742. Min Range: -1.7742

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1001088 (The Pile)

Max Activating Token Index: 521