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

Dataset: The Pile

Neuron 3262 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: 1.1763. Min Range: -1.1763

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1820521 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1037142 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0534. Min Act: -0.0000

Data Index: 726289 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1013533 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.1302. Min Act: -0.0000

Data Index: 33681 (The Pile)

Max Activating Token Index: 81

Text #5

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9600. Min Act: -0.0000

Data Index: 653901 (The Pile)

Max Activating Token Index: 929

Text #6

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0570. Min Act: -0.0000

Data Index: 1335258 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1331572 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9786. Min Act: -0.0000

Data Index: 294561 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9798. Min Act: -0.0000

Data Index: 432443 (The Pile)

Max Activating Token Index: 761

Text #10

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1041238 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1825533 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1115220 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0358. Min Act: -0.0000

Data Index: 792713 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.1019. Min Act: -0.0000

Data Index: 755703 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1491771 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0529. Min Act: -0.0000

Data Index: 1861097 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1717662 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 1.1763. Min Range: -1.1763

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1371370 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 1.1763. Min Range: -1.1763

Max Act: 1.0114. Min Act: -0.0000

Data Index: 1615830 (The Pile)

Max Activating Token Index: 700