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

Dataset: The Pile

Neuron 407 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1934062 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.9656. Min Act: -0.0000

Data Index: 801242 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1133069 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.8872. Min Act: -0.0000

Data Index: 82520 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.8657. Min Act: -0.0000

Data Index: 488298 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1911188 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.8317. Min Act: -0.0000

Data Index: 859705 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7652. Min Act: -0.0000

Data Index: 225632 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1525746 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1352782 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7866. Min Act: -0.0000

Data Index: 487726 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.8368. Min Act: -0.0000

Data Index: 838135 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1221404 (The Pile)

Max Activating Token Index: 905

Text #13

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1913356 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7142. Min Act: -0.0000

Data Index: 856088 (The Pile)

Max Activating Token Index: 230

Text #15

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7927. Min Act: -0.0000

Data Index: 1966405 (The Pile)

Max Activating Token Index: 808

Text #16

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7511. Min Act: -0.0000

Data Index: 1133897 (The Pile)

Max Activating Token Index: 258

Text #17

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1464393 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1861441 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7176. Min Act: -0.0000

Data Index: 415927 (The Pile)

Max Activating Token Index: 825