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

Dataset: The Pile

Neuron 2918 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.8710. Min Act: -0.0000

Data Index: 1177599 (The Pile)

Max Activating Token Index: 304

Text #1

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.7031. Min Act: -0.0000

Data Index: 247398 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.6936. Min Act: -0.0000

Data Index: 677874 (The Pile)

Max Activating Token Index: 710

Text #3

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.7040. Min Act: -0.0000

Data Index: 394670 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5522. Min Act: -0.0000

Data Index: 47637 (The Pile)

Max Activating Token Index: 882

Text #5

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5336. Min Act: -0.0000

Data Index: 722075 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3608. Min Act: -0.0000

Data Index: 13239 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.4442. Min Act: -0.0000

Data Index: 689893 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.7065. Min Act: -0.0000

Data Index: 1692555 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5637. Min Act: -0.0000

Data Index: 267316 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5629. Min Act: -0.0000

Data Index: 18959 (The Pile)

Max Activating Token Index: 606

Text #11

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3092. Min Act: -0.0000

Data Index: 285528 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.4323. Min Act: -0.0000

Data Index: 225639 (The Pile)

Max Activating Token Index: 423

Text #13

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.4312. Min Act: -0.0000

Data Index: 1509805 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3674. Min Act: -0.0000

Data Index: 1946578 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1083349 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2243. Min Act: -0.0000

Data Index: 808732 (The Pile)

Max Activating Token Index: 911

Text #17

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2710. Min Act: -0.0000

Data Index: 1665019 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.4227. Min Act: -0.0000

Data Index: 1795650 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5855. Min Act: -0.0000

Data Index: 1274668 (The Pile)

Max Activating Token Index: 951