Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5474 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.3859. Min Act: -0.0000

Data Index: 588377 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.1746. Min Act: -0.0000

Data Index: 908883 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.9922. Min Act: -0.0000

Data Index: 915675 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.2387. Min Act: -0.0000

Data Index: 519470 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.1786. Min Act: -0.0000

Data Index: 1346707 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.1756. Min Act: -0.0000

Data Index: 558517 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.1161. Min Act: -0.0000

Data Index: 1088607 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.0505. Min Act: -0.0000

Data Index: 36967 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 3.3859. Min Range: -3.3859

Max Act: 3.0397. Min Act: -0.0000

Data Index: 479915 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.9950. Min Act: -0.0000

Data Index: 955492 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.8442. Min Act: -0.0000

Data Index: 26021 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.9797. Min Act: -0.0000

Data Index: 204429 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.9673. Min Act: -0.0000

Data Index: 383508 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.8039. Min Act: -0.0000

Data Index: 347452 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.7611. Min Act: -0.0000

Data Index: 1146750 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.8909. Min Act: -0.0000

Data Index: 1050481 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.7351. Min Act: -0.0000

Data Index: 350785 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.8558. Min Act: -0.0000

Data Index: 44797 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.8284. Min Act: -0.0000

Data Index: 856465 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 3.3859. Min Range: -3.3859

Max Act: 2.7023. Min Act: -0.0000

Data Index: 844133 (C4 (Web Text))

Max Activating Token Index: 933