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

Dataset: The Pile

Neuron 234 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.9622. Min Act: -0.0000

Data Index: 309584 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1798505 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.8547. Min Act: -0.0000

Data Index: 463743 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.8373. Min Act: -0.0000

Data Index: 223586 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.8174. Min Act: -0.0000

Data Index: 449908 (The Pile)

Max Activating Token Index: 941

Text #5

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1556402 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1576945 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.8274. Min Act: -0.0000

Data Index: 149890 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1194787 (The Pile)

Max Activating Token Index: 973

Text #9

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7705. Min Act: -0.0000

Data Index: 890043 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1957871 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1486682 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1826485 (The Pile)

Max Activating Token Index: 508

Text #13

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1139786 (The Pile)

Max Activating Token Index: 507

Text #14

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7607. Min Act: -0.0000

Data Index: 348855 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1496791 (The Pile)

Max Activating Token Index: 179

Text #16

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1153726 (The Pile)

Max Activating Token Index: 581

Text #17

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7076. Min Act: -0.0000

Data Index: 106180 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7162. Min Act: -0.0000

Data Index: 316858 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1259662 (The Pile)

Max Activating Token Index: 402