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

Dataset: The Pile

Neuron 4528 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: 1.1220. Min Range: -1.1220

Max Act: 1.1220. Min Act: -0.0000

Data Index: 327591 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1420743 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1377158 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0603. Min Act: -0.0000

Data Index: 74410 (The Pile)

Max Activating Token Index: 895

Text #4

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1939826 (The Pile)

Max Activating Token Index: 630

Text #5

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9420. Min Act: -0.0000

Data Index: 891639 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1109089 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1165829 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9653. Min Act: -0.0000

Data Index: 408566 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9326. Min Act: -0.0000

Data Index: 426794 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9222. Min Act: -0.0000

Data Index: 810292 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9097. Min Act: -0.0000

Data Index: 374196 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1955608 (The Pile)

Max Activating Token Index: 792

Text #13

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1155793 (The Pile)

Max Activating Token Index: 360

Text #14

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1438331 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1340628 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1663697 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8966. Min Act: -0.0000

Data Index: 20261 (The Pile)

Max Activating Token Index: 783

Text #18

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1866334 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8591. Min Act: -0.0000

Data Index: 860785 (The Pile)

Max Activating Token Index: 492