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

Dataset: The Pile

Neuron 4003 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1129. Min Act: -0.0000

Data Index: 35599 (The Pile)

Max Activating Token Index: 92

Text #1

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1637607 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9788. Min Act: -0.0000

Data Index: 648509 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1093023 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0070. Min Act: -0.0000

Data Index: 480936 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0825. Min Act: -0.0000

Data Index: 338973 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9563. Min Act: -0.0000

Data Index: 646853 (The Pile)

Max Activating Token Index: 101

Text #7

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1393009 (The Pile)

Max Activating Token Index: 95

Text #8

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1302534 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0606. Min Act: -0.0000

Data Index: 362110 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1229021 (The Pile)

Max Activating Token Index: 522

Text #11

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0419. Min Act: -0.0000

Data Index: 481566 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9832. Min Act: -0.0000

Data Index: 702203 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1924228 (The Pile)

Max Activating Token Index: 203

Text #14

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.8938. Min Act: -0.0000

Data Index: 652396 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9886. Min Act: -0.0000

Data Index: 8521 (The Pile)

Max Activating Token Index: 616

Text #16

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9555. Min Act: -0.0000

Data Index: 692759 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.1748. Min Range: -1.1748

Max Act: 1.0566. Min Act: -0.0001

Data Index: 913762 (The Pile)

Max Activating Token Index: 921

Text #18

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9342. Min Act: -0.0000

Data Index: 1871132 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 1.1748. Min Range: -1.1748

Max Act: 0.9478. Min Act: -0.0000

Data Index: 475172 (The Pile)

Max Activating Token Index: 160