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

Dataset: The Pile

Neuron 3637 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: 1.5952. Min Range: -1.5952

Max Act: 1.5952. Min Act: -0.0000

Data Index: 560430 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4607. Min Act: -0.0000

Data Index: 293938 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.3556. Min Act: -0.0000

Data Index: 822715 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.4009. Min Act: -0.0000

Data Index: 1493628 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.3116. Min Act: -0.0000

Data Index: 1245379 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1347391 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2888. Min Act: -0.0000

Data Index: 461963 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.1961. Min Act: -0.0000

Data Index: 817504 (The Pile)

Max Activating Token Index: 426

Text #8

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.1624. Min Act: -0.0000

Data Index: 1778251 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2621. Min Act: -0.0000

Data Index: 786006 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2316. Min Act: -0.0000

Data Index: 1737407 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2314. Min Act: -0.0000

Data Index: 1719805 (The Pile)

Max Activating Token Index: 643

Text #12

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1307395 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2227. Min Act: -0.0000

Data Index: 181534 (The Pile)

Max Activating Token Index: 191

Text #14

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1074374 (The Pile)

Max Activating Token Index: 181

Text #15

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2095. Min Act: -0.0000

Data Index: 871721 (The Pile)

Max Activating Token Index: 685

Text #16

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.2076. Min Act: -0.0000

Data Index: 211743 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.1274. Min Act: -0.0000

Data Index: 1436125 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.1918. Min Act: -0.0000

Data Index: 839035 (The Pile)

Max Activating Token Index: 534

Text #19

Max Range: 1.5952. Min Range: -1.5952

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1093668 (The Pile)

Max Activating Token Index: 670