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

Dataset: The Pile

Neuron 38 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: 1.3433. Min Range: -1.3433

Max Act: 1.3068. Min Act: -0.0000

Data Index: 658374 (The Pile)

Max Activating Token Index: 207

Text #1

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.3433. Min Act: -0.0000

Data Index: 747604 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.2567. Min Act: -0.0000

Data Index: 736642 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1909. Min Act: -0.0000

Data Index: 1831808 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1017156 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1723180 (The Pile)

Max Activating Token Index: 291

Text #6

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1632. Min Act: -0.0000

Data Index: 441236 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1846. Min Act: -0.0000

Data Index: 941247 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1110590 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1733. Min Act: -0.0000

Data Index: 1016433 (The Pile)

Max Activating Token Index: 307

Text #10

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.0986. Min Act: -0.0000

Data Index: 650451 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1836408 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1373. Min Act: -0.0000

Data Index: 421465 (The Pile)

Max Activating Token Index: 216

Text #13

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1105938 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1893930 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1952. Min Act: -0.0000

Data Index: 447103 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.1097. Min Act: -0.0000

Data Index: 1988259 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.0861. Min Act: -0.0000

Data Index: 223397 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 1.3433. Min Range: -1.3433

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1257092 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 1.3433. Min Range: -1.3433

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1293732 (The Pile)

Max Activating Token Index: 952