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

Dataset: The Pile

Neuron 1951 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: 0.0765. Min Range: -0.0765

Max Act: 0.0765. Min Act: 0.0000

Data Index: 1647175 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0733. Min Act: 0.0000

Data Index: 1627292 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0701. Min Act: 0.0000

Data Index: 1970776 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1393906 (The Pile)

Max Activating Token Index: 240

Text #4

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0680. Min Act: 0.0000

Data Index: 803537 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0662. Min Act: 0.0000

Data Index: 636562 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0638. Min Act: 0.0000

Data Index: 1064944 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0628. Min Act: 0.0000

Data Index: 786305 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0625. Min Act: -0.0000

Data Index: 41078 (The Pile)

Max Activating Token Index: 511

Text #9

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0622. Min Act: 0.0000

Data Index: 137455 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0579. Min Act: -0.0000

Data Index: 586728 (The Pile)

Max Activating Token Index: 676

Text #11

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0599. Min Act: 0.0000

Data Index: 1145999 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0584. Min Act: 0.0000

Data Index: 521917 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0585. Min Act: 0.0000

Data Index: 486580 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0584. Min Act: 0.0000

Data Index: 1175371 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0603. Min Act: 0.0000

Data Index: 1538090 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0578. Min Act: 0.0000

Data Index: 718079 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1977450 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0576. Min Act: 0.0000

Data Index: 617048 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1848956 (The Pile)

Max Activating Token Index: 699