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

Dataset: The Pile

Neuron 1985 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: 0.9654. Min Range: -0.9654

Max Act: 0.9654. Min Act: -0.0000

Data Index: 574912 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1562075 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1671085 (The Pile)

Max Activating Token Index: 88

Text #3

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8512. Min Act: -0.0000

Data Index: 906835 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1942167 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8492. Min Act: -0.0000

Data Index: 786549 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1849397 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7520. Min Act: -0.0000

Data Index: 44539 (The Pile)

Max Activating Token Index: 403

Text #8

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1920024 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7749. Min Act: -0.0000

Data Index: 322250 (The Pile)

Max Activating Token Index: 834

Text #10

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1690280 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1234030 (The Pile)

Max Activating Token Index: 750

Text #12

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7855. Min Act: -0.0000

Data Index: 598768 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1547776 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1865173 (The Pile)

Max Activating Token Index: 26

Text #15

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7381. Min Act: -0.0000

Data Index: 288330 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7933. Min Act: -0.0000

Data Index: 24484 (The Pile)

Max Activating Token Index: 38

Text #17

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1383456 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7572. Min Act: -0.0000

Data Index: 314635 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 0.9654. Min Range: -0.9654

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1583039 (The Pile)

Max Activating Token Index: 527