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

Dataset: The Pile

Neuron 3723 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1205. Min Act: -0.0000

Data Index: 594316 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1287743 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1915168 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1825034 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0898. Min Act: -0.0000

Data Index: 863625 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1454064 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0920. Min Act: -0.0000

Data Index: 693603 (The Pile)

Max Activating Token Index: 359

Text #7

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0917. Min Act: -0.0000

Data Index: 773951 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0912. Min Act: -0.0000

Data Index: 61273 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1745010 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0867. Min Act: -0.0000

Data Index: 48938 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1091431 (The Pile)

Max Activating Token Index: 175

Text #12

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1306572 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0852. Min Act: -0.0000

Data Index: 668321 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0879. Min Act: -0.0000

Data Index: 45275 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1239864 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1952110 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0847. Min Act: -0.0000

Data Index: 222635 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1032683 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0837. Min Act: -0.0000

Data Index: 303401 (The Pile)

Max Activating Token Index: 182