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

Dataset: The Pile

Neuron 3111 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.6198. Min Act: -0.0000

Data Index: 1790552 (The Pile)

Max Activating Token Index: 64

Text #1

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.4273. Min Act: -0.0000

Data Index: 983605 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.4568. Min Act: -0.0000

Data Index: 1998029 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.4109. Min Act: -0.0000

Data Index: 528878 (The Pile)

Max Activating Token Index: 139

Text #4

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3690. Min Act: -0.0000

Data Index: 400239 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3464. Min Act: -0.0000

Data Index: 1150968 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3523. Min Act: -0.0000

Data Index: 749724 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1739680 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3741. Min Act: -0.0000

Data Index: 1266223 (The Pile)

Max Activating Token Index: 645

Text #9

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2761. Min Act: -0.0000

Data Index: 687736 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1468043 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1856849 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1822006 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3088. Min Act: -0.0000

Data Index: 754552 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1313158 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2901. Min Act: -0.0000

Data Index: 162391 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1667214 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2635. Min Act: -0.0000

Data Index: 1294774 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.2665. Min Act: -0.0000

Data Index: 1681055 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 1.6198. Min Range: -1.6198

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1818809 (The Pile)

Max Activating Token Index: 873