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

Dataset: The Pile

Neuron 1310 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: 1.1418. Min Range: -1.1418

Max Act: 1.1290. Min Act: -0.0000

Data Index: 705219 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.1418. Min Act: -0.0000

Data Index: 695982 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.0886. Min Act: -0.0000

Data Index: 94709 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1260387 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.0788. Min Act: -0.0000

Data Index: 107974 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1394745 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.0587. Min Act: -0.0000

Data Index: 786097 (The Pile)

Max Activating Token Index: 870

Text #7

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.0103. Min Act: -0.0000

Data Index: 562978 (The Pile)

Max Activating Token Index: 701

Text #8

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9788. Min Act: -0.0000

Data Index: 212293 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9892. Min Act: -0.0000

Data Index: 15337 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9503. Min Act: -0.0000

Data Index: 1813734 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9511. Min Act: -0.0000

Data Index: 733692 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 1.1418. Min Range: -1.1418

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1349812 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1274782 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8666. Min Act: -0.0000

Data Index: 846502 (The Pile)

Max Activating Token Index: 852

Text #15

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9436. Min Act: -0.0000

Data Index: 664749 (The Pile)

Max Activating Token Index: 945

Text #16

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.8851. Min Act: -0.0000

Data Index: 771832 (The Pile)

Max Activating Token Index: 1009

Text #17

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9030. Min Act: -0.0000

Data Index: 50405 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1178268 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 1.1418. Min Range: -1.1418

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1812689 (The Pile)

Max Activating Token Index: 110