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

Dataset: The Pile

Neuron 3688 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: 5.1320. Min Range: -5.1320

Max Act: 5.1320. Min Act: -0.0000

Data Index: 1477082 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 5.1320. Min Range: -5.1320

Max Act: 4.9839. Min Act: -0.0000

Data Index: 1972277 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 5.1320. Min Range: -5.1320

Max Act: 4.5527. Min Act: -0.0000

Data Index: 687868 (The Pile)

Max Activating Token Index: 600

Text #3

Max Range: 5.1320. Min Range: -5.1320

Max Act: 4.5782. Min Act: -0.0000

Data Index: 1570301 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 5.1320. Min Range: -5.1320

Max Act: 4.0052. Min Act: 0.0000

Data Index: 935533 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 5.1320. Min Range: -5.1320

Max Act: 4.0785. Min Act: -0.0000

Data Index: 1641091 (The Pile)

Max Activating Token Index: 562

Text #6

Max Range: 5.1320. Min Range: -5.1320

Max Act: 4.0703. Min Act: -0.0000

Data Index: 668477 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 5.1320. Min Range: -5.1320

Max Act: 4.1904. Min Act: -0.0000

Data Index: 1370273 (The Pile)

Max Activating Token Index: 78

Text #8

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.9984. Min Act: -0.0000

Data Index: 1549469 (The Pile)

Max Activating Token Index: 557

Text #9

Max Range: 5.1320. Min Range: -5.1320

Max Act: 4.1544. Min Act: -0.0000

Data Index: 894127 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 5.1320. Min Range: -5.1320

Max Act: 4.0119. Min Act: -0.0000

Data Index: 310489 (The Pile)

Max Activating Token Index: 237

Text #11

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.9660. Min Act: -0.0000

Data Index: 700675 (The Pile)

Max Activating Token Index: 650

Text #12

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.8833. Min Act: -0.0000

Data Index: 1922457 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.8521. Min Act: -0.0000

Data Index: 1521956 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.6770. Min Act: -0.0000

Data Index: 235256 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.9912. Min Act: -0.0000

Data Index: 1074173 (The Pile)

Max Activating Token Index: 574

Text #16

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.9470. Min Act: -0.0000

Data Index: 538601 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.7550. Min Act: -0.0000

Data Index: 438501 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.6052. Min Act: -0.0000

Data Index: 291464 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 5.1320. Min Range: -5.1320

Max Act: 3.7484. Min Act: -0.0000

Data Index: 133416 (The Pile)

Max Activating Token Index: 60