Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3414 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8743. Min Act: -0.0000

Data Index: 877606 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1067227 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7968. Min Act: -0.0000

Data Index: 224303 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1248824 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7887. Min Act: -0.0000

Data Index: 1344245 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7363. Min Act: -0.0000

Data Index: 237527 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1698310 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7322. Min Act: -0.0000

Data Index: 735522 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1884160 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1601086 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6719. Min Act: -0.0000

Data Index: 206834 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7114. Min Act: -0.0000

Data Index: 957119 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6426. Min Act: -0.0000

Data Index: 204434 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6206. Min Act: -0.0000

Data Index: 637477 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6568. Min Act: -0.0000

Data Index: 351021 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6689. Min Act: -0.0000

Data Index: 629660 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6764. Min Act: -0.0000

Data Index: 883720 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1021580 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1167181 (The Pile)

Max Activating Token Index: 740

Text #19

Max Range: 0.8743. Min Range: -0.8743

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1226976 (The Pile)

Max Activating Token Index: 871