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

Dataset: The Pile

Neuron 2917 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: 1.8231. Min Range: -1.8231

Max Act: 1.8231. Min Act: -0.0000

Data Index: 1620697 (The Pile)

Max Activating Token Index: 821

Text #1

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6974. Min Act: -0.0000

Data Index: 934704 (The Pile)

Max Activating Token Index: 718

Text #2

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.7945. Min Act: -0.0000

Data Index: 1441816 (The Pile)

Max Activating Token Index: 806

Text #3

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.7184. Min Act: -0.0000

Data Index: 138905 (The Pile)

Max Activating Token Index: 345

Text #4

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.7192. Min Act: -0.0000

Data Index: 562078 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.7013. Min Act: -0.0000

Data Index: 903541 (The Pile)

Max Activating Token Index: 648

Text #6

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6156. Min Act: -0.0000

Data Index: 671510 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.6466. Min Act: -0.0000

Data Index: 158126 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.4685. Min Act: -0.0000

Data Index: 90751 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.4454. Min Act: -0.0000

Data Index: 1654941 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.4254. Min Act: -0.0000

Data Index: 361401 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5113. Min Act: -0.0000

Data Index: 894389 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.5898. Min Act: -0.0000

Data Index: 1723679 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.7053. Min Act: -0.0000

Data Index: 617125 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.4550. Min Act: -0.0000

Data Index: 325708 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.3582. Min Act: -0.0000

Data Index: 240659 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1784211 (The Pile)

Max Activating Token Index: 93

Text #17

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.4965. Min Act: -0.0000

Data Index: 1166534 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.4584. Min Act: -0.0000

Data Index: 743214 (The Pile)

Max Activating Token Index: 626

Text #19

Max Range: 1.8231. Min Range: -1.8231

Max Act: 1.4405. Min Act: -0.0000

Data Index: 230228 (The Pile)

Max Activating Token Index: 856