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

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

Neuron 3492 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6758. Min Act: -0.0000

Data Index: 129683 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6420. Min Act: -0.0000

Data Index: 790889 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6523. Min Act: -0.0000

Data Index: 96008 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6449. Min Act: -0.0000

Data Index: 46760 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1277488 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1313161 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6770. Min Act: -0.0000

Data Index: 780032 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1047696 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5988. Min Act: -0.0000

Data Index: 432861 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1004441 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5844. Min Act: -0.0000

Data Index: 668257 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5851. Min Act: -0.0000

Data Index: 977788 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5379. Min Act: -0.0000

Data Index: 122090 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5732. Min Act: -0.0000

Data Index: 596573 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1305379 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1238781 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1315720 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5317. Min Act: -0.0000

Data Index: 667413 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.5212. Min Act: -0.0000

Data Index: 865734 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.6770. Min Range: -0.6770

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1063466 (C4 (Web Text))

Max Activating Token Index: 610