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

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

Neuron 408 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1337. Min Act: -0.0000

Data Index: 22106 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1099. Min Act: -0.0000

Data Index: 800251 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0807. Min Act: -0.0000

Data Index: 538683 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0723. Min Act: -0.0000

Data Index: 778398 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0638. Min Act: -0.0000

Data Index: 649544 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0702. Min Act: -0.0000

Data Index: 325283 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1022601 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0715. Min Act: -0.0000

Data Index: 850193 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0683. Min Act: -0.0000

Data Index: 924753 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0678. Min Act: -0.0000

Data Index: 680935 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1075277 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0684. Min Act: -0.0000

Data Index: 417986 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0658. Min Act: -0.0000

Data Index: 603934 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1245531 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0615. Min Act: -0.0000

Data Index: 71551 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0612. Min Act: -0.0000

Data Index: 476168 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0604. Min Act: -0.0000

Data Index: 231309 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1253604 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1247457 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1004849 (C4 (Web Text))

Max Activating Token Index: 385