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

Dataset: The Pile

Neuron 726 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: 0.2400. Min Range: -0.2400

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1069798 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2400. Min Act: -0.0000

Data Index: 370639 (The Pile)

Max Activating Token Index: 467

Text #2

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2351. Min Act: -0.0000

Data Index: 850409 (The Pile)

Max Activating Token Index: 213

Text #3

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2268. Min Act: -0.0000

Data Index: 428462 (The Pile)

Max Activating Token Index: 289

Text #4

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2259. Min Act: -0.0000

Data Index: 521147 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1142004 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1764789 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2359. Min Act: -0.0000

Data Index: 616097 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2095. Min Act: -0.0000

Data Index: 229684 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2028. Min Act: -0.0000

Data Index: 663159 (The Pile)

Max Activating Token Index: 934

Text #10

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1954501 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1004326 (The Pile)

Max Activating Token Index: 516

Text #12

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1389631 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2263. Min Act: -0.0000

Data Index: 205448 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1613288 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2087. Min Act: -0.0000

Data Index: 252062 (The Pile)

Max Activating Token Index: 364

Text #16

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2037. Min Act: -0.0000

Data Index: 796542 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1093589 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2143. Min Act: -0.0000

Data Index: 858273 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 0.2400. Min Range: -0.2400

Max Act: 0.2060. Min Act: -0.0000

Data Index: 760951 (The Pile)

Max Activating Token Index: 129