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

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

Neuron 2408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.1785. Min Act: -0.0000

Data Index: 889401 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0576. Min Act: -0.0000

Data Index: 70658 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0555. Min Act: -0.0001

Data Index: 607621 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0578. Min Act: -0.0000

Data Index: 706025 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0428. Min Act: -0.0001

Data Index: 496524 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0459. Min Act: -0.0000

Data Index: 611147 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0405. Min Act: -0.0000

Data Index: 299305 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0418. Min Act: -0.0000

Data Index: 913820 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1263937 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1075127 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0434. Min Act: -0.0000

Data Index: 1094832 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0399. Min Act: -0.0000

Data Index: 1054208 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0342. Min Act: -0.0000

Data Index: 160261 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1219123 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0371. Min Act: -0.0001

Data Index: 198357 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0412. Min Act: -0.0000

Data Index: 353649 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0332. Min Act: -0.0001

Data Index: 643619 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0372. Min Act: -0.0000

Data Index: 544572 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1025718 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.1785. Min Range: -0.1785

Max Act: 0.0358. Min Act: -0.0000

Data Index: 324525 (C4 (Web Text))

Max Activating Token Index: 425