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

Dataset: The Pile

Neuron 3705 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: 1.8839. Min Range: -1.8839

Max Act: 1.7141. Min Act: -0.0000

Data Index: 622053 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.6801. Min Act: -0.0000

Data Index: 88899 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.7146. Min Act: -0.0000

Data Index: 1887478 (The Pile)

Max Activating Token Index: 819

Text #3

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.8839. Min Act: -0.0000

Data Index: 692644 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.7173. Min Act: -0.0000

Data Index: 1357126 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.6441. Min Act: -0.0000

Data Index: 1907398 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.7273. Min Act: -0.0000

Data Index: 334649 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.6045. Min Act: -0.0000

Data Index: 1172870 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.7958. Min Act: -0.0000

Data Index: 1471205 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.6991. Min Act: -0.0000

Data Index: 215611 (The Pile)

Max Activating Token Index: 912

Text #10

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5438. Min Act: -0.0000

Data Index: 1475111 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5549. Min Act: -0.0000

Data Index: 1624073 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1089644 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5322. Min Act: -0.0000

Data Index: 640028 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.6101. Min Act: -0.0000

Data Index: 275447 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.4731. Min Act: -0.0000

Data Index: 1628444 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5999. Min Act: -0.0000

Data Index: 706803 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5538. Min Act: -0.0000

Data Index: 2472 (The Pile)

Max Activating Token Index: 870

Text #18

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5493. Min Act: -0.0000

Data Index: 562887 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5095. Min Act: -0.0000

Data Index: 1258367 (The Pile)

Max Activating Token Index: 286