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

Dataset: The Pile

Neuron 2714 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1672787 (The Pile)

Max Activating Token Index: 318

Text #1

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1979579 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.9226. Min Act: -0.0000

Data Index: 725510 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1949861 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.9137. Min Act: -0.0000

Data Index: 100739 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.8200. Min Act: -0.0000

Data Index: 543702 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1195106 (The Pile)

Max Activating Token Index: 823

Text #7

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1913392 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.8441. Min Act: -0.0000

Data Index: 181441 (The Pile)

Max Activating Token Index: 467

Text #9

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7984. Min Act: -0.0000

Data Index: 705600 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1035624 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1005546 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1077635 (The Pile)

Max Activating Token Index: 970

Text #13

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7604. Min Act: -0.0000

Data Index: 1566251 (The Pile)

Max Activating Token Index: 157

Text #14

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1943229 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1333716 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.6480. Min Act: -0.0000

Data Index: 320557 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1017933 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1385269 (The Pile)

Max Activating Token Index: 376

Text #19

Max Range: 0.9871. Min Range: -0.9871

Max Act: 0.7056. Min Act: -0.0000

Data Index: 881983 (The Pile)

Max Activating Token Index: 294