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

Dataset: The Pile

Neuron 4047 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7323. Min Act: -0.0000

Data Index: 372267 (The Pile)

Max Activating Token Index: 939

Text #1

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.8774. Min Act: -0.0000

Data Index: 344444 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1952840 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1000293 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6820. Min Act: -0.0000

Data Index: 189800 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.7003. Min Act: -0.0000

Data Index: 92611 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1779041 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6220. Min Act: -0.0000

Data Index: 485307 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6239. Min Act: -0.0000

Data Index: 900752 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1620745 (The Pile)

Max Activating Token Index: 581

Text #10

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1530124 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5986. Min Act: -0.0000

Data Index: 618625 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5952. Min Act: -0.0000

Data Index: 600668 (The Pile)

Max Activating Token Index: 554

Text #13

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1534044 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6249. Min Act: -0.0000

Data Index: 471275 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.6012. Min Act: -0.0000

Data Index: 346190 (The Pile)

Max Activating Token Index: 879

Text #16

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1833428 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5274. Min Act: -0.0000

Data Index: 19606 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5029. Min Act: -0.0000

Data Index: 774035 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.8774. Min Range: -0.8774

Max Act: 0.5702. Min Act: -0.0000

Data Index: 577384 (The Pile)

Max Activating Token Index: 601