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

Dataset: The Pile

Neuron 3071 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: 1.2112. Min Range: -1.2112

Max Act: 1.2037. Min Act: -0.0000

Data Index: 474091 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 1.2112. Min Range: -1.2112

Max Act: 1.2112. Min Act: -0.0000

Data Index: 1333635 (The Pile)

Max Activating Token Index: 973

Text #2

Max Range: 1.2112. Min Range: -1.2112

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1899291 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 1.2112. Min Range: -1.2112

Max Act: 1.0021. Min Act: -0.0000

Data Index: 901067 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1138504 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 1.2112. Min Range: -1.2112

Max Act: 1.0036. Min Act: 0.0000

Data Index: 1551296 (The Pile)

Max Activating Token Index: 558

Text #6

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1373228 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9401. Min Act: -0.0000

Data Index: 608973 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8738. Min Act: -0.0000

Data Index: 128892 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8971. Min Act: -0.0000

Data Index: 164893 (The Pile)

Max Activating Token Index: 589

Text #10

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1684555 (The Pile)

Max Activating Token Index: 643

Text #11

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8893. Min Act: -0.0000

Data Index: 1970776 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8812. Min Act: -0.0000

Data Index: 789126 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8627. Min Act: -0.0000

Data Index: 130536 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1465302 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1130946 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1603363 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1651604 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.8415. Min Act: -0.0000

Data Index: 972258 (The Pile)

Max Activating Token Index: 474

Text #19

Max Range: 1.2112. Min Range: -1.2112

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1664366 (The Pile)

Max Activating Token Index: 792