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

Dataset: The Pile

Neuron 3387 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.3927. Min Act: -0.0000

Data Index: 855738 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9038. Min Act: -0.0000

Data Index: 267991 (The Pile)

Max Activating Token Index: 577

Text #2

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0419. Min Act: -0.0000

Data Index: 834687 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9951. Min Act: -0.0000

Data Index: 385314 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1239537 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1278225 (The Pile)

Max Activating Token Index: 791

Text #6

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1846054 (The Pile)

Max Activating Token Index: 693

Text #7

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1058012 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9535. Min Act: -0.0000

Data Index: 284344 (The Pile)

Max Activating Token Index: 510

Text #9

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1968694 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9969. Min Act: -0.0000

Data Index: 412942 (The Pile)

Max Activating Token Index: 5

Text #11

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9012. Min Act: -0.0000

Data Index: 638322 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9685. Min Act: -0.0000

Data Index: 793449 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1261946 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9097. Min Act: -0.0000

Data Index: 752429 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 1.3927. Min Range: -1.3927

Max Act: 1.0100. Min Act: -0.0000

Data Index: 789251 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1556371 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.9254. Min Act: -0.0000

Data Index: 541937 (The Pile)

Max Activating Token Index: 75

Text #18

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1498593 (The Pile)

Max Activating Token Index: 210

Text #19

Max Range: 1.3927. Min Range: -1.3927

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1400076 (The Pile)

Max Activating Token Index: 341