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

Dataset: The Pile

Neuron 1104 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.8713. Min Act: -0.0000

Data Index: 487718 (The Pile)

Max Activating Token Index: 487

Text #1

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.8678. Min Act: -0.0000

Data Index: 509073 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 2.0077. Min Range: -2.0077

Max Act: 2.0077. Min Act: -0.0000

Data Index: 1633355 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.6964. Min Act: -0.0000

Data Index: 1683518 (The Pile)

Max Activating Token Index: 635

Text #4

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.6430. Min Act: -0.0000

Data Index: 235463 (The Pile)

Max Activating Token Index: 42

Text #5

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.6508. Min Act: -0.0000

Data Index: 610762 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5002. Min Act: -0.0000

Data Index: 1385412 (The Pile)

Max Activating Token Index: 907

Text #7

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.5993. Min Act: -0.0000

Data Index: 1060262 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4740. Min Act: -0.0000

Data Index: 468156 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.7137. Min Act: -0.0000

Data Index: 810250 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.3468. Min Act: -0.0000

Data Index: 522694 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.3604. Min Act: -0.0000

Data Index: 125707 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4239. Min Act: -0.0000

Data Index: 556084 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1545041 (The Pile)

Max Activating Token Index: 152

Text #14

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.4208. Min Act: -0.0000

Data Index: 622350 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.2565. Min Act: -0.0000

Data Index: 1588758 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.3852. Min Act: -0.0000

Data Index: 45020 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.3810. Min Act: -0.0000

Data Index: 43079 (The Pile)

Max Activating Token Index: 926

Text #18

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.3268. Min Act: -0.0000

Data Index: 58277 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 2.0077. Min Range: -2.0077

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1236139 (The Pile)

Max Activating Token Index: 384