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

Dataset: The Pile

Neuron 3347 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: 0.9782. Min Range: -0.9782

Max Act: 0.9437. Min Act: -0.0000

Data Index: 879949 (The Pile)

Max Activating Token Index: 830

Text #1

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9782. Min Act: -0.0000

Data Index: 204091 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1291615 (The Pile)

Max Activating Token Index: 842

Text #3

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1874869 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8538. Min Act: 0.0000

Data Index: 1316554 (The Pile)

Max Activating Token Index: 37

Text #5

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1557256 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8666. Min Act: -0.0000

Data Index: 409152 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8478. Min Act: -0.0000

Data Index: 437201 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8419. Min Act: -0.0000

Data Index: 583639 (The Pile)

Max Activating Token Index: 857

Text #9

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8349. Min Act: -0.0000

Data Index: 410774 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1116952 (The Pile)

Max Activating Token Index: 285

Text #11

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1404587 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9146. Min Act: 0.0000

Data Index: 983380 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1020575 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1354610 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8140. Min Act: 0.0000

Data Index: 12693 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7872. Min Act: 0.0000

Data Index: 1992507 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7455. Min Act: -0.0000

Data Index: 1543298 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7282. Min Act: 0.0000

Data Index: 637686 (The Pile)

Max Activating Token Index: 218

Text #19

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7472. Min Act: -0.0000

Data Index: 496679 (The Pile)

Max Activating Token Index: 431