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

Dataset: The Pile

Neuron 1997 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8904. Min Act: -0.0000

Data Index: 527723 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.9636. Min Act: -0.0000

Data Index: 308184 (The Pile)

Max Activating Token Index: 571

Text #2

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8009. Min Act: -0.0000

Data Index: 582769 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8657. Min Act: -0.0000

Data Index: 573636 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1197272 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1507053 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7568. Min Act: -0.0000

Data Index: 402848 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1429545 (The Pile)

Max Activating Token Index: 896

Text #8

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1001696 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7568. Min Act: -0.0000

Data Index: 577923 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8252. Min Act: -0.0000

Data Index: 24885 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7451. Min Act: -0.0000

Data Index: 543792 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1703900 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1183629 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.6996. Min Act: -0.0000

Data Index: 210208 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7132. Min Act: -0.0000

Data Index: 684726 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1412916 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1991014 (The Pile)

Max Activating Token Index: 868

Text #18

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1042289 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 0.9636. Min Range: -0.9636

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1935665 (The Pile)

Max Activating Token Index: 731