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

Dataset: The Pile

Neuron 339 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: 1.0145. Min Range: -1.0145

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1441001 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.9798. Min Act: -0.0000

Data Index: 361363 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.9702. Min Act: -0.0000

Data Index: 742479 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.9376. Min Act: -0.0000

Data Index: 1012504 (The Pile)

Max Activating Token Index: 594

Text #4

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1304662 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1838908 (The Pile)

Max Activating Token Index: 435

Text #6

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.9100. Min Act: -0.0000

Data Index: 125797 (The Pile)

Max Activating Token Index: 660

Text #7

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1032923 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.9135. Min Act: -0.0000

Data Index: 121772 (The Pile)

Max Activating Token Index: 789

Text #9

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1657238 (The Pile)

Max Activating Token Index: 189

Text #10

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8963. Min Act: -0.0000

Data Index: 129873 (The Pile)

Max Activating Token Index: 507

Text #11

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1216521 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1071113 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8997. Min Act: -0.0000

Data Index: 178050 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8762. Min Act: -0.0000

Data Index: 1501860 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.9005. Min Act: -0.0000

Data Index: 576560 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1482705 (The Pile)

Max Activating Token Index: 940

Text #17

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8622. Min Act: -0.0000

Data Index: 432878 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1096768 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1377665 (The Pile)

Max Activating Token Index: 918