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

Dataset: The Pile

Neuron 308 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: 0.4142. Min Range: -0.4142

Max Act: 0.4142. Min Act: -0.0000

Data Index: 729348 (The Pile)

Max Activating Token Index: 861

Text #1

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1263126 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1728152 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1098535 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.2783. Min Act: -0.0000

Data Index: 103562 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3315. Min Act: -0.0000

Data Index: 500767 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3375. Min Act: -0.0000

Data Index: 67589 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3458. Min Act: -0.0000

Data Index: 951340 (The Pile)

Max Activating Token Index: 618

Text #8

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3182. Min Act: -0.0000

Data Index: 1971117 (The Pile)

Max Activating Token Index: 417

Text #9

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3418. Min Act: -0.0000

Data Index: 1640908 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1595918 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1033016 (The Pile)

Max Activating Token Index: 392

Text #12

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1082059 (The Pile)

Max Activating Token Index: 509

Text #13

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3051. Min Act: -0.0000

Data Index: 361564 (The Pile)

Max Activating Token Index: 474

Text #14

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3010. Min Act: -0.0000

Data Index: 195638 (The Pile)

Max Activating Token Index: 871

Text #15

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3122. Min Act: -0.0000

Data Index: 676753 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1871516 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.2695. Min Act: -0.0000

Data Index: 258905 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3169. Min Act: -0.0000

Data Index: 327937 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 0.4142. Min Range: -0.4142

Max Act: 0.3197. Min Act: -0.0000

Data Index: 608509 (The Pile)

Max Activating Token Index: 494