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

Dataset: The Pile

Neuron 2024 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: 0.9473. Min Range: -0.9473

Max Act: 0.9473. Min Act: -0.0000

Data Index: 743140 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1321540 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1598582 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1273101 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1113614 (The Pile)

Max Activating Token Index: 713

Text #5

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.7497. Min Act: -0.0000

Data Index: 711190 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.6688. Min Act: -0.0000

Data Index: 843039 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1626280 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.6499. Min Act: -0.0000

Data Index: 232689 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1699193 (The Pile)

Max Activating Token Index: 554

Text #10

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.6661. Min Act: -0.0000

Data Index: 793691 (The Pile)

Max Activating Token Index: 614

Text #11

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.5724. Min Act: -0.0000

Data Index: 729854 (The Pile)

Max Activating Token Index: 658

Text #12

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1195489 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.6097. Min Act: -0.0000

Data Index: 225276 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1896521 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1123104 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1479521 (The Pile)

Max Activating Token Index: 156

Text #17

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.5745. Min Act: -0.0000

Data Index: 218660 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1646714 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 0.9473. Min Range: -0.9473

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1788027 (The Pile)

Max Activating Token Index: 1005