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

Dataset: The Pile

Neuron 3286 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.9420. Min Act: -0.0000

Data Index: 397706 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.7917. Min Act: -0.0000

Data Index: 278123 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.7509. Min Act: -0.0000

Data Index: 897596 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.7095. Min Act: -0.0000

Data Index: 2907 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1058385 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6977. Min Act: -0.0000

Data Index: 714318 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6713. Min Act: -0.0000

Data Index: 411047 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1914036 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6237. Min Act: -0.0000

Data Index: 771481 (The Pile)

Max Activating Token Index: 631

Text #9

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1055444 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6445. Min Act: -0.0000

Data Index: 48435 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6595. Min Act: -0.0000

Data Index: 93126 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6305. Min Act: -0.0000

Data Index: 862986 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6190. Min Act: -0.0000

Data Index: 831060 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.5982. Min Act: -0.0000

Data Index: 181503 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6126. Min Act: -0.0000

Data Index: 394788 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1640261 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6302. Min Act: -0.0000

Data Index: 896180 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1288894 (The Pile)

Max Activating Token Index: 961

Text #19

Max Range: 0.9420. Min Range: -0.9420

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1070499 (The Pile)

Max Activating Token Index: 637