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

Dataset: The Pile

Neuron 400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.2976. Min Act: -0.0000

Data Index: 1269104 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.2660. Min Act: -0.0000

Data Index: 1919348 (The Pile)

Max Activating Token Index: 530

Text #2

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1637. Min Act: -0.0000

Data Index: 973601 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1040380 (The Pile)

Max Activating Token Index: 559

Text #4

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1280. Min Act: -0.0000

Data Index: 76811 (The Pile)

Max Activating Token Index: 862

Text #5

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1790. Min Act: -0.0000

Data Index: 1203383 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1440. Min Act: -0.0000

Data Index: 641854 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.1151. Min Act: -0.0000

Data Index: 1593368 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.0985. Min Act: -0.0000

Data Index: 329645 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.0678. Min Act: -0.0000

Data Index: 82791 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 1.2976. Min Range: -1.2976

Max Act: 0.9860. Min Act: -0.0000

Data Index: 832163 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.0122. Min Act: -0.0000

Data Index: 704666 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1430233 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 1.2976. Min Range: -1.2976

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1042567 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 1.2976. Min Range: -1.2976

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1941757 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 1.2976. Min Range: -1.2976

Max Act: 0.9401. Min Act: -0.0000

Data Index: 899102 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 1.2976. Min Range: -1.2976

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1305807 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 1.2976. Min Range: -1.2976

Max Act: 0.9889. Min Act: -0.0000

Data Index: 984295 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 1.2976. Min Range: -1.2976

Max Act: 0.9838. Min Act: -0.0000

Data Index: 20416 (The Pile)

Max Activating Token Index: 768

Text #19

Max Range: 1.2976. Min Range: -1.2976

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1965554 (The Pile)

Max Activating Token Index: 572