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

Dataset: The Pile

Neuron 1294 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.1289. Min Act: -0.0001

Data Index: 533803 (The Pile)

Max Activating Token Index: 349

Text #1

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.0525. Min Act: -0.0000

Data Index: 66980 (The Pile)

Max Activating Token Index: 706

Text #2

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1185747 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9042. Min Act: -0.0000

Data Index: 199630 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1379210 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8211. Min Act: -0.0000

Data Index: 26313 (The Pile)

Max Activating Token Index: 828

Text #6

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8268. Min Act: -0.0000

Data Index: 589984 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1824262 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7686. Min Act: -0.0000

Data Index: 479076 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7783. Min Act: -0.0000

Data Index: 218134 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1249925 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7022. Min Act: -0.0000

Data Index: 1388658 (The Pile)

Max Activating Token Index: 843

Text #12

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1939653 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1732804 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.6802. Min Act: -0.0000

Data Index: 627058 (The Pile)

Max Activating Token Index: 42

Text #15

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7577. Min Act: -0.0000

Data Index: 588922 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.6913. Min Act: -0.0000

Data Index: 980081 (The Pile)

Max Activating Token Index: 216

Text #17

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1632788 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.7375. Min Act: -0.0000

Data Index: 1489652 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1067404 (The Pile)

Max Activating Token Index: 730