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

Dataset: The Pile

Neuron 4905 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: 0.9342. Min Range: -0.9342

Max Act: 0.9342. Min Act: -0.0000

Data Index: 1067711 (The Pile)

Max Activating Token Index: 203

Text #1

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.8837. Min Act: -0.0000

Data Index: 482146 (The Pile)

Max Activating Token Index: 557

Text #2

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1513182 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.8815. Min Act: -0.0000

Data Index: 685798 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.7643. Min Act: -0.0000

Data Index: 610438 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.7714. Min Act: -0.0000

Data Index: 265823 (The Pile)

Max Activating Token Index: 602

Text #6

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.7694. Min Act: -0.0000

Data Index: 450084 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.7462. Min Act: -0.0000

Data Index: 115316 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.7387. Min Act: -0.0000

Data Index: 716636 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.6550. Min Act: -0.0000

Data Index: 204160 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1436660 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.6874. Min Act: -0.0000

Data Index: 499988 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.7471. Min Act: -0.0000

Data Index: 835717 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1626380 (The Pile)

Max Activating Token Index: 121

Text #14

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.6841. Min Act: -0.0000

Data Index: 662756 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1986236 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.6958. Min Act: -0.0000

Data Index: 970227 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1038476 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1999372 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.9342. Min Range: -0.9342

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1476101 (The Pile)

Max Activating Token Index: 506