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

Dataset: The Pile

Neuron 4561 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.2636. Min Act: -0.0000

Data Index: 1730033 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.0007. Min Act: -0.0000

Data Index: 1289227 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1507056 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7880. Min Act: -0.0000

Data Index: 450636 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1195218 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 1.2636. Min Range: -1.2636

Max Act: 1.1505. Min Act: -0.0000

Data Index: 914924 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1593682 (The Pile)

Max Activating Token Index: 238

Text #7

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7179. Min Act: -0.0000

Data Index: 393010 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7945. Min Act: -0.0000

Data Index: 676140 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7257. Min Act: -0.0000

Data Index: 142604 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7348. Min Act: -0.0000

Data Index: 195319 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1571342 (The Pile)

Max Activating Token Index: 893

Text #12

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.8495. Min Act: -0.0000

Data Index: 319885 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1267310 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7342. Min Act: -0.0000

Data Index: 383886 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7148. Min Act: -0.0000

Data Index: 351488 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1579030 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.6998. Min Act: -0.0000

Data Index: 923036 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1213085 (The Pile)

Max Activating Token Index: 797

Text #19

Max Range: 1.2636. Min Range: -1.2636

Max Act: 0.6670. Min Act: -0.0000

Data Index: 310842 (The Pile)

Max Activating Token Index: 460