Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 795 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8847. Min Act: -0.0000

Data Index: 444244 (The Pile)

Max Activating Token Index: 141

Text #1

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8958. Min Act: -0.0000

Data Index: 207995 (The Pile)

Max Activating Token Index: 244

Text #2

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1574493 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.9306. Min Act: -0.0000

Data Index: 402888 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8416. Min Act: -0.0000

Data Index: 574393 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1972717 (The Pile)

Max Activating Token Index: 142

Text #6

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1274703 (The Pile)

Max Activating Token Index: 484

Text #7

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7966. Min Act: -0.0000

Data Index: 805124 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1037088 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8715. Min Act: -0.0000

Data Index: 1407768 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1110307 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8096. Min Act: -0.0000

Data Index: 59754 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8252. Min Act: -0.0000

Data Index: 342805 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8524. Min Act: -0.0000

Data Index: 935368 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8447. Min Act: -0.0000

Data Index: 917925 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8325. Min Act: -0.0000

Data Index: 682754 (The Pile)

Max Activating Token Index: 430

Text #16

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8384. Min Act: -0.0000

Data Index: 454374 (The Pile)

Max Activating Token Index: 631

Text #17

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8396. Min Act: -0.0000

Data Index: 545169 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1829672 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 0.9306. Min Range: -0.9306

Max Act: 0.7742. Min Act: -0.0000

Data Index: 507178 (The Pile)

Max Activating Token Index: 504