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

Dataset: The Pile

Neuron 2564 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0881. Min Range: -1.0881

Max Act: 1.0881. Min Act: -0.0000

Data Index: 1508064 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9636. Min Act: -0.0000

Data Index: 498447 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1591079 (The Pile)

Max Activating Token Index: 924

Text #3

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1970996 (The Pile)

Max Activating Token Index: 463

Text #4

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9124. Min Act: -0.0000

Data Index: 409516 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1767968 (The Pile)

Max Activating Token Index: 632

Text #6

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.9034. Min Act: -0.0000

Data Index: 50764 (The Pile)

Max Activating Token Index: 615

Text #7

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8076. Min Act: -0.0000

Data Index: 393760 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8505. Min Act: -0.0000

Data Index: 114246 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1542722 (The Pile)

Max Activating Token Index: 892

Text #10

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8936. Min Act: -0.0000

Data Index: 497506 (The Pile)

Max Activating Token Index: 916

Text #11

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8380. Min Act: -0.0000

Data Index: 784850 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1823828 (The Pile)

Max Activating Token Index: 520

Text #13

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1825236 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1633109 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.7381. Min Act: -0.0000

Data Index: 385947 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1836622 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8620. Min Act: -0.0000

Data Index: 680502 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8078. Min Act: -0.0000

Data Index: 493764 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 1.0881. Min Range: -1.0881

Max Act: 0.8582. Min Act: -0.0000

Data Index: 652542 (The Pile)

Max Activating Token Index: 220