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

Dataset: The Pile

Neuron 1719 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1426419 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1761981 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1474575 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8411. Min Act: -0.0000

Data Index: 840291 (The Pile)

Max Activating Token Index: 420

Text #4

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8219. Min Act: -0.0000

Data Index: 529970 (The Pile)

Max Activating Token Index: 116

Text #5

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8534. Min Act: -0.0000

Data Index: 426758 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7810. Min Act: -0.0000

Data Index: 567924 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1707201 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.8152. Min Act: -0.0000

Data Index: 735594 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7679. Min Act: -0.0000

Data Index: 664343 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1523945 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1354257 (The Pile)

Max Activating Token Index: 395

Text #12

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1401230 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1295193 (The Pile)

Max Activating Token Index: 671

Text #14

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7507. Min Act: -0.0000

Data Index: 893608 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7252. Min Act: -0.0000

Data Index: 283295 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1442749 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7206. Min Act: -0.0000

Data Index: 372669 (The Pile)

Max Activating Token Index: 956

Text #18

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.7349. Min Act: -0.0000

Data Index: 519019 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 0.8736. Min Range: -0.8736

Max Act: 0.6999. Min Act: -0.0000

Data Index: 804975 (The Pile)

Max Activating Token Index: 745