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

Dataset: The Pile

Neuron 1445 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: 0.7770. Min Range: -0.7770

Max Act: 0.7770. Min Act: -0.0000

Data Index: 133911 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1540885 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7092. Min Act: -0.0000

Data Index: 436330 (The Pile)

Max Activating Token Index: 283

Text #3

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7216. Min Act: -0.0000

Data Index: 141241 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7100. Min Act: -0.0000

Data Index: 61362 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7082. Min Act: -0.0000

Data Index: 663984 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7011. Min Act: -0.0000

Data Index: 428697 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6968. Min Act: -0.0000

Data Index: 436247 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6924. Min Act: -0.0000

Data Index: 410746 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7112. Min Act: -0.0000

Data Index: 300243 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1078256 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7067. Min Act: -0.0000

Data Index: 234491 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6778. Min Act: -0.0000

Data Index: 293904 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1734605 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6662. Min Act: -0.0000

Data Index: 611237 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6854. Min Act: -0.0000

Data Index: 978614 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6847. Min Act: -0.0000

Data Index: 284427 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6604. Min Act: -0.0000

Data Index: 325310 (The Pile)

Max Activating Token Index: 981

Text #18

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1908897 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1290827 (The Pile)

Max Activating Token Index: 900