Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2011 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.1521. Min Act: -0.0000

Data Index: 1562401 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1335533 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.0888. Min Act: -0.0000

Data Index: 1978691 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.0491. Min Act: -0.0000

Data Index: 1929309 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1669577 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.0227. Min Act: -0.0000

Data Index: 1085775 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1741949 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 1.1521. Min Range: -1.1521

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1254678 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1614694 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1541674 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9417. Min Act: -0.0000

Data Index: 904593 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8667. Min Act: -0.0000

Data Index: 716766 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1746382 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8789. Min Act: -0.0000

Data Index: 437923 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1025895 (The Pile)

Max Activating Token Index: 674

Text #15

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.9067. Min Act: -0.0000

Data Index: 792015 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8433. Min Act: -0.0000

Data Index: 528419 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8977. Min Act: -0.0000

Data Index: 871483 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1134762 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 1.1521. Min Range: -1.1521

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1107683 (The Pile)

Max Activating Token Index: 235