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

Dataset: The Pile

Neuron 3074 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1609520 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8236. Min Act: -0.0000

Data Index: 939272 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1624191 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1729932 (The Pile)

Max Activating Token Index: 711

Text #4

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7277. Min Act: 0.0000

Data Index: 692571 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7618. Min Act: -0.0000

Data Index: 958636 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1869275 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7495. Min Act: -0.0000

Data Index: 534507 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7248. Min Act: -0.0000

Data Index: 381734 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7269. Min Act: 0.0000

Data Index: 1175108 (The Pile)

Max Activating Token Index: 636

Text #10

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1549240 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7394. Min Act: -0.0000

Data Index: 662031 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6957. Min Act: -0.0000

Data Index: 349463 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6926. Min Act: -0.0000

Data Index: 341454 (The Pile)

Max Activating Token Index: 164

Text #14

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6944. Min Act: -0.0000

Data Index: 537584 (The Pile)

Max Activating Token Index: 574

Text #15

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7061. Min Act: -0.0000

Data Index: 206834 (The Pile)

Max Activating Token Index: 752

Text #16

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7058. Min Act: 0.0000

Data Index: 1099105 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1315323 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1351838 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6322. Min Act: 0.0000

Data Index: 1893119 (The Pile)

Max Activating Token Index: 477