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

Dataset: The Pile

Neuron 4145 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: 1.1276. Min Range: -1.1276

Max Act: 1.1276. Min Act: -0.0000

Data Index: 349011 (The Pile)

Max Activating Token Index: 491

Text #1

Max Range: 1.1276. Min Range: -1.1276

Max Act: 1.1087. Min Act: -0.0000

Data Index: 226391 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 1.1276. Min Range: -1.1276

Max Act: 1.0783. Min Act: -0.0000

Data Index: 405899 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 1.1276. Min Range: -1.1276

Max Act: 1.0451. Min Act: -0.0000

Data Index: 600121 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9433. Min Act: -0.0000

Data Index: 945567 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 1.1276. Min Range: -1.1276

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1876732 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8871. Min Act: -0.0000

Data Index: 312389 (The Pile)

Max Activating Token Index: 387

Text #7

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1766107 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9415. Min Act: -0.0000

Data Index: 745169 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8719. Min Act: -0.0000

Data Index: 1925748 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1155768 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9114. Min Act: -0.0000

Data Index: 705070 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8936. Min Act: -0.0000

Data Index: 948448 (The Pile)

Max Activating Token Index: 850

Text #13

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8699. Min Act: -0.0000

Data Index: 838918 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1542884 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8470. Min Act: -0.0000

Data Index: 1452479 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8300. Min Act: -0.0000

Data Index: 536261 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8344. Min Act: -0.0000

Data Index: 298422 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1309853 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1598912 (The Pile)

Max Activating Token Index: 575