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

Dataset: The Pile

Neuron 2398 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.8813. Min Act: -0.0000

Data Index: 685106 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.8140. Min Act: -0.0000

Data Index: 594492 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6340. Min Act: -0.0000

Data Index: 308376 (The Pile)

Max Activating Token Index: 461

Text #3

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7109. Min Act: -0.0000

Data Index: 967695 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1836092 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1059131 (The Pile)

Max Activating Token Index: 743

Text #6

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1383409 (The Pile)

Max Activating Token Index: 791

Text #7

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6839. Min Act: -0.0000

Data Index: 811808 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1392914 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1281066 (The Pile)

Max Activating Token Index: 69

Text #10

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1788289 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1185884 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6555. Min Act: -0.0000

Data Index: 525986 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.5735. Min Act: -0.0000

Data Index: 761074 (The Pile)

Max Activating Token Index: 162

Text #14

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6042. Min Act: -0.0000

Data Index: 362042 (The Pile)

Max Activating Token Index: 530

Text #15

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.4960. Min Act: -0.0000

Data Index: 701622 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1087865 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.5992. Min Act: -0.0000

Data Index: 530954 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.5784. Min Act: -0.0000

Data Index: 915640 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.5354. Min Act: -0.0000

Data Index: 321216 (The Pile)

Max Activating Token Index: 199