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

Dataset: The Pile

Neuron 1148 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: 1.1871. Min Range: -1.1871

Max Act: 1.1871. Min Act: -0.0000

Data Index: 724066 (The Pile)

Max Activating Token Index: 732

Text #1

Max Range: 1.1871. Min Range: -1.1871

Max Act: 1.0166. Min Act: -0.0000

Data Index: 1482664 (The Pile)

Max Activating Token Index: 950

Text #2

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1380523 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.9444. Min Act: -0.0000

Data Index: 324783 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8341. Min Act: -0.0000

Data Index: 76651 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8429. Min Act: -0.0000

Data Index: 706763 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1059411 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8016. Min Act: -0.0000

Data Index: 349132 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8914. Min Act: -0.0000

Data Index: 613443 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8234. Min Act: -0.0000

Data Index: 1101637 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1021361 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8043. Min Act: -0.0000

Data Index: 874186 (The Pile)

Max Activating Token Index: 1004

Text #12

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1860959 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7907. Min Act: -0.0000

Data Index: 828718 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1476324 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7736. Min Act: -0.0000

Data Index: 381615 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1613816 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7891. Min Act: -0.0000

Data Index: 207622 (The Pile)

Max Activating Token Index: 779

Text #18

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1423784 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 1.1871. Min Range: -1.1871

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1374232 (The Pile)

Max Activating Token Index: 285