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

Dataset: The Pile

Neuron 585 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1287058 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1123437 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1645490 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0792. Min Act: -0.0000

Data Index: 580461 (The Pile)

Max Activating Token Index: 986

Text #4

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0704. Min Act: -0.0000

Data Index: 1674614 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0655. Min Act: -0.0000

Data Index: 327922 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1549343 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1780881 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0652. Min Act: -0.0000

Data Index: 956705 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1250362 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1176768 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0644. Min Act: -0.0000

Data Index: 364080 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1990792 (The Pile)

Max Activating Token Index: 949

Text #13

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1333431 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1850021 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0669. Min Act: -0.0000

Data Index: 925334 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1634265 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0592. Min Act: -0.0000

Data Index: 689348 (The Pile)

Max Activating Token Index: 932

Text #18

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0607. Min Act: -0.0000

Data Index: 832060 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 0.1089. Min Range: -0.1089

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1501789 (The Pile)

Max Activating Token Index: 946