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

Dataset: The Pile

Neuron 47 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.4632. Min Act: -0.0000

Data Index: 155176 (The Pile)

Max Activating Token Index: 589

Text #1

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1637895 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2997. Min Act: -0.0000

Data Index: 603654 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2637. Min Act: -0.0000

Data Index: 427046 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1941817 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.2607. Min Act: -0.0000

Data Index: 641906 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1440011 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0632. Min Act: -0.0000

Data Index: 1260644 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0367. Min Act: -0.0000

Data Index: 1891515 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1559124 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1476871 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9991. Min Act: -0.0000

Data Index: 1704149 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9786. Min Act: -0.0000

Data Index: 706817 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1000507 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1229458 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0252. Min Act: -0.0000

Data Index: 55280 (The Pile)

Max Activating Token Index: 169

Text #16

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.8423. Min Act: -0.0000

Data Index: 369991 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.9826. Min Act: -0.0001

Data Index: 510224 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 1.4632. Min Range: -1.4632

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1279909 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 1.4632. Min Range: -1.4632

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1476674 (The Pile)

Max Activating Token Index: 44