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

Dataset: The Pile

Neuron 3564 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: 0.8974. Min Range: -0.8974

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1879839 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1143496 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8524. Min Act: -0.0000

Data Index: 555131 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1205822 (The Pile)

Max Activating Token Index: 727

Text #4

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7942. Min Act: -0.0000

Data Index: 759109 (The Pile)

Max Activating Token Index: 675

Text #5

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8171. Min Act: -0.0000

Data Index: 650574 (The Pile)

Max Activating Token Index: 506

Text #6

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1960183 (The Pile)

Max Activating Token Index: 829

Text #7

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8727. Min Act: -0.0000

Data Index: 256833 (The Pile)

Max Activating Token Index: 719

Text #8

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.8172. Min Act: -0.0000

Data Index: 262924 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1293664 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7533. Min Act: -0.0000

Data Index: 425933 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7956. Min Act: -0.0000

Data Index: 61889 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1945663 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1048589 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7560. Min Act: -0.0000

Data Index: 488916 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7885. Min Act: -0.0000

Data Index: 575918 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1825929 (The Pile)

Max Activating Token Index: 283

Text #17

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1024187 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1628860 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 0.8974. Min Range: -0.8974

Max Act: 0.6768. Min Act: -0.0000

Data Index: 33309 (The Pile)

Max Activating Token Index: 741