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

Dataset: The Pile

Neuron 462 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9139. Min Range: -5.9139

Max Act: 5.7883. Min Act: -0.0000

Data Index: 744040 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 5.9139. Min Range: -5.9139

Max Act: 5.9139. Min Act: -0.0000

Data Index: 1073762 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 5.9139. Min Range: -5.9139

Max Act: 5.5873. Min Act: -0.0000

Data Index: 1283132 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 5.9139. Min Range: -5.9139

Max Act: 5.2306. Min Act: -0.0000

Data Index: 327109 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 5.9139. Min Range: -5.9139

Max Act: 5.5743. Min Act: -0.0000

Data Index: 718346 (The Pile)

Max Activating Token Index: 483

Text #5

Max Range: 5.9139. Min Range: -5.9139

Max Act: 5.3805. Min Act: -0.0000

Data Index: 533658 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 5.9139. Min Range: -5.9139

Max Act: 5.2653. Min Act: -0.0000

Data Index: 688709 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.8942. Min Act: -0.0000

Data Index: 665115 (The Pile)

Max Activating Token Index: 252

Text #8

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.9560. Min Act: -0.0000

Data Index: 1742482 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.7571. Min Act: -0.0000

Data Index: 1177522 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.8564. Min Act: -0.0000

Data Index: 98743 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.9736. Min Act: -0.0000

Data Index: 1324981 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.9860. Min Act: -0.0000

Data Index: 925986 (The Pile)

Max Activating Token Index: 537

Text #13

Max Range: 5.9139. Min Range: -5.9139

Max Act: 5.2725. Min Act: -0.0000

Data Index: 632336 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.9362. Min Act: -0.0000

Data Index: 400174 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.7655. Min Act: -0.0000

Data Index: 1775062 (The Pile)

Max Activating Token Index: 322

Text #16

Max Range: 5.9139. Min Range: -5.9139

Max Act: 5.2585. Min Act: -0.0000

Data Index: 2498 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.8840. Min Act: -0.0000

Data Index: 1481593 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.8807. Min Act: -0.0000

Data Index: 1432395 (The Pile)

Max Activating Token Index: 593

Text #19

Max Range: 5.9139. Min Range: -5.9139

Max Act: 4.5357. Min Act: -0.0000

Data Index: 681426 (The Pile)

Max Activating Token Index: 216