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

Dataset: The Pile

Neuron 1962 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3607. Min Range: -1.3607

Max Act: 1.3607. Min Act: -0.0000

Data Index: 768996 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.9650. Min Act: -0.0000

Data Index: 434927 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1083291 (The Pile)

Max Activating Token Index: 644

Text #3

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.9674. Min Act: -0.0000

Data Index: 1554694 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.8379. Min Act: -0.0000

Data Index: 378867 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1860275 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1023908 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1122432 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1402609 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.8303. Min Act: -0.0000

Data Index: 526372 (The Pile)

Max Activating Token Index: 554

Text #10

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1334816 (The Pile)

Max Activating Token Index: 238

Text #11

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.7668. Min Act: -0.0000

Data Index: 1630416 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.8081. Min Act: -0.0000

Data Index: 17161 (The Pile)

Max Activating Token Index: 522

Text #13

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1859880 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1487367 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1687119 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.7168. Min Act: -0.0000

Data Index: 646216 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1515555 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1321865 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 1.3607. Min Range: -1.3607

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1604934 (The Pile)

Max Activating Token Index: 675