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

Dataset: The Pile

Neuron 1291 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: 0.3289. Min Range: -0.3289

Max Act: 0.3289. Min Act: -0.0000

Data Index: 1282375 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2986. Min Act: -0.0000

Data Index: 379275 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1964314 (The Pile)

Max Activating Token Index: 867

Text #3

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2299. Min Act: -0.0000

Data Index: 394899 (The Pile)

Max Activating Token Index: 641

Text #4

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1950550 (The Pile)

Max Activating Token Index: 270

Text #5

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2323. Min Act: -0.0000

Data Index: 799621 (The Pile)

Max Activating Token Index: 266

Text #6

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1276917 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2535. Min Act: -0.0000

Data Index: 742071 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1812155 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1646514 (The Pile)

Max Activating Token Index: 627

Text #10

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2169. Min Act: -0.0000

Data Index: 972116 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1977143 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2266. Min Act: -0.0000

Data Index: 818487 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1965. Min Act: 0.0000

Data Index: 79961 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1943. Min Act: -0.0000

Data Index: 880059 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1691657 (The Pile)

Max Activating Token Index: 765

Text #16

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1797. Min Act: -0.0000

Data Index: 325405 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1077545 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1241090 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1723. Min Act: -0.0000

Data Index: 225503 (The Pile)

Max Activating Token Index: 193