Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3727 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1859. Min Act: -0.0000

Data Index: 36790 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1811672 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1473322 (The Pile)

Max Activating Token Index: 174

Text #3

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1358790 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1037532 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1290499 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1180034 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1237. Min Act: -0.0000

Data Index: 714030 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1239. Min Act: -0.0000

Data Index: 10310 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1820888 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1223. Min Act: -0.0000

Data Index: 869917 (The Pile)

Max Activating Token Index: 413

Text #11

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1104. Min Act: -0.0000

Data Index: 561861 (The Pile)

Max Activating Token Index: 893

Text #12

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1973322 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1192. Min Act: -0.0000

Data Index: 925198 (The Pile)

Max Activating Token Index: 648

Text #14

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1165. Min Act: -0.0000

Data Index: 894611 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.0898. Min Act: -0.0000

Data Index: 704483 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1156698 (The Pile)

Max Activating Token Index: 795

Text #17

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1080. Min Act: -0.0000

Data Index: 618614 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1191. Min Act: -0.0000

Data Index: 999683 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 0.1859. Min Range: -0.1859

Max Act: 0.1183. Min Act: -0.0000

Data Index: 1372238 (The Pile)

Max Activating Token Index: 612