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

Dataset: The Pile

Neuron 3172 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: 1.1501. Min Range: -1.1501

Max Act: 1.1501. Min Act: -0.0000

Data Index: 454328 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.9032. Min Act: -0.0000

Data Index: 88678 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.8317. Min Act: -0.0000

Data Index: 105001 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1708206 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.7228. Min Act: -0.0000

Data Index: 616187 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1987107 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.7763. Min Act: -0.0000

Data Index: 766353 (The Pile)

Max Activating Token Index: 854

Text #7

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.7656. Min Act: -0.0000

Data Index: 444830 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1347638 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6505. Min Act: -0.0000

Data Index: 637662 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.7012. Min Act: -0.0000

Data Index: 867095 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6941. Min Act: 0.0000

Data Index: 1305722 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1095160 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6556. Min Act: -0.0000

Data Index: 38144 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.7020. Min Act: -0.0000

Data Index: 607597 (The Pile)

Max Activating Token Index: 12

Text #15

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1538469 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6263. Min Act: -0.0000

Data Index: 287331 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1506231 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6428. Min Act: -0.0000

Data Index: 975285 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 1.1501. Min Range: -1.1501

Max Act: 0.6250. Min Act: -0.0000

Data Index: 477849 (The Pile)

Max Activating Token Index: 1018