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

Dataset: The Pile

Neuron 4399 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1756782 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5202. Min Act: -0.0000

Data Index: 61495 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4797. Min Act: -0.0000

Data Index: 78367 (The Pile)

Max Activating Token Index: 97

Text #3

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4804. Min Act: -0.0000

Data Index: 1889274 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4499. Min Act: -0.0000

Data Index: 262372 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1037582 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1074428 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4161. Min Act: -0.0000

Data Index: 448042 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1071332 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1506556 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1179789 (The Pile)

Max Activating Token Index: 870

Text #11

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4059. Min Act: -0.0000

Data Index: 471212 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1011823 (The Pile)

Max Activating Token Index: 99

Text #13

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4091. Min Act: -0.0000

Data Index: 1860200 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3924. Min Act: -0.0000

Data Index: 536813 (The Pile)

Max Activating Token Index: 693

Text #15

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3888. Min Act: -0.0000

Data Index: 799893 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3864. Min Act: -0.0000

Data Index: 496387 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3819. Min Act: -0.0000

Data Index: 211041 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1346938 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3616. Min Act: -0.0000

Data Index: 245265 (The Pile)

Max Activating Token Index: 626