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

Dataset: The Pile

Neuron 781 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1389549 (The Pile)

Max Activating Token Index: 496

Text #1

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1456824 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1574830 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6008. Min Act: -0.0000

Data Index: 599978 (The Pile)

Max Activating Token Index: 554

Text #4

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6294. Min Act: 0.0000

Data Index: 1764286 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1523395 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1473212 (The Pile)

Max Activating Token Index: 749

Text #7

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1743555 (The Pile)

Max Activating Token Index: 781

Text #8

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5984. Min Act: -0.0000

Data Index: 1701299 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5997. Min Act: -0.0000

Data Index: 738108 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5882. Min Act: 0.0000

Data Index: 174435 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1536661 (The Pile)

Max Activating Token Index: 182

Text #12

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1832562 (The Pile)

Max Activating Token Index: 773

Text #13

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.6088. Min Act: -0.0000

Data Index: 933777 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5312. Min Act: 0.0000

Data Index: 464930 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5613. Min Act: -0.0000

Data Index: 156104 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1978857 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5965. Min Act: -0.0000

Data Index: 935422 (The Pile)

Max Activating Token Index: 288

Text #18

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1056174 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 0.7072. Min Range: -0.7072

Max Act: 0.5499. Min Act: 0.0000

Data Index: 341224 (The Pile)

Max Activating Token Index: 787