Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 267 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2502. Min Act: 0.0000

Data Index: 1427651 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1791471 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1682687 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1918663 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2302. Min Act: -0.0000

Data Index: 640174 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1583864 (The Pile)

Max Activating Token Index: 125

Text #6

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2291. Min Act: -0.0000

Data Index: 509212 (The Pile)

Max Activating Token Index: 930

Text #7

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1944841 (The Pile)

Max Activating Token Index: 196

Text #8

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1203147 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2200. Min Act: -0.0000

Data Index: 3040 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2202. Min Act: -0.0000

Data Index: 914140 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1441204 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1584234 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1971763 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1140347 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2080. Min Act: -0.0001

Data Index: 1922050 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2233. Min Act: -0.0000

Data Index: 848842 (The Pile)

Max Activating Token Index: 379

Text #17

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1529181 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2272. Min Act: 0.0000

Data Index: 1234533 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 0.2510. Min Range: -0.2510

Max Act: 0.2189. Min Act: -0.0000

Data Index: 859068 (The Pile)

Max Activating Token Index: 743