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

Dataset: The Pile

Neuron 3993 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.8176. Min Act: -0.0000

Data Index: 99328 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1628726 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.7495. Min Act: -0.0000

Data Index: 444247 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1824888 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.7049. Min Act: -0.0000

Data Index: 630872 (The Pile)

Max Activating Token Index: 736

Text #5

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1283364 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6531. Min Act: -0.0000

Data Index: 83968 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.7020. Min Act: -0.0000

Data Index: 580099 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1747634 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5836. Min Act: -0.0000

Data Index: 303360 (The Pile)

Max Activating Token Index: 297

Text #10

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5772. Min Act: -0.0000

Data Index: 354892 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1612644 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5523. Min Act: -0.0000

Data Index: 863519 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5925. Min Act: -0.0000

Data Index: 800897 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1519988 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5564. Min Act: -0.0000

Data Index: 849582 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1101946 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1531417 (The Pile)

Max Activating Token Index: 921

Text #18

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5815. Min Act: -0.0000

Data Index: 1827842 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5676. Min Act: -0.0000

Data Index: 93014 (The Pile)

Max Activating Token Index: 890