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

Dataset: The Pile

Neuron 872 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0275. Min Range: -5.0275

Max Act: 5.0275. Min Act: -0.0000

Data Index: 1912154 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.8800. Min Act: -0.0000

Data Index: 586523 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.3677. Min Act: -0.0000

Data Index: 766719 (The Pile)

Max Activating Token Index: 723

Text #3

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.6892. Min Act: -0.0000

Data Index: 1380454 (The Pile)

Max Activating Token Index: 12

Text #4

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.5180. Min Act: -0.0000

Data Index: 1311919 (The Pile)

Max Activating Token Index: 975

Text #5

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.3329. Min Act: -0.0000

Data Index: 1363306 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.3905. Min Act: -0.0000

Data Index: 116720 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.5523. Min Act: -0.0000

Data Index: 1860999 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.2019. Min Act: -0.0000

Data Index: 1146239 (The Pile)

Max Activating Token Index: 932

Text #9

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.6887. Min Act: -0.0000

Data Index: 802195 (The Pile)

Max Activating Token Index: 979

Text #10

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.5106. Min Act: -0.0000

Data Index: 1549359 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.5008. Min Act: -0.0000

Data Index: 1712836 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.4617. Min Act: -0.0000

Data Index: 341233 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.4485. Min Act: -0.0000

Data Index: 1233536 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.4409. Min Act: -0.0000

Data Index: 5347 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.4305. Min Act: -0.0000

Data Index: 958777 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.4289. Min Act: -0.0000

Data Index: 683223 (The Pile)

Max Activating Token Index: 31

Text #17

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.5976. Min Act: -0.0000

Data Index: 110978 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.2602. Min Act: -0.0000

Data Index: 1686527 (The Pile)

Max Activating Token Index: 405

Text #19

Max Range: 5.0275. Min Range: -5.0275

Max Act: 4.4021. Min Act: -0.0000

Data Index: 902449 (The Pile)

Max Activating Token Index: 27