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

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

Neuron 4516 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0608. Min Range: -2.0608

Max Act: 2.0608. Min Act: -0.0000

Data Index: 541021 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.7953. Min Act: -0.0000

Data Index: 1142753 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.6053. Min Act: -0.0000

Data Index: 274638 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.5999. Min Act: -0.0000

Data Index: 991344 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1194364 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.5575. Min Act: -0.0000

Data Index: 256891 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1054738 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.5455. Min Act: -0.0000

Data Index: 490936 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.5508. Min Act: -0.0000

Data Index: 917593 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.3985. Min Act: -0.0000

Data Index: 816282 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1213849 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.4798. Min Act: -0.0000

Data Index: 388936 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.5537. Min Act: -0.0000

Data Index: 839558 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.3796. Min Act: -0.0000

Data Index: 974911 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.5317. Min Act: -0.0000

Data Index: 320118 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.4340. Min Act: -0.0000

Data Index: 933807 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.4325. Min Act: -0.0000

Data Index: 401068 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.4302. Min Act: -0.0000

Data Index: 140998 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.4084. Min Act: -0.0000

Data Index: 404037 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 2.0608. Min Range: -2.0608

Max Act: 1.4216. Min Act: -0.0000

Data Index: 553543 (C4 (Web Text))

Max Activating Token Index: 739