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

Dataset: The Pile

Neuron 4998 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2521. Min Act: -0.0000

Data Index: 240266 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2415. Min Act: -0.0000

Data Index: 447091 (The Pile)

Max Activating Token Index: 306

Text #2

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1694641 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2438. Min Act: -0.0000

Data Index: 937701 (The Pile)

Max Activating Token Index: 459

Text #4

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2333. Min Act: -0.0000

Data Index: 326883 (The Pile)

Max Activating Token Index: 567

Text #5

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2092. Min Act: -0.0000

Data Index: 979392 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1160079 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1336507 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1037315 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2082. Min Act: -0.0000

Data Index: 169868 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2171. Min Act: -0.0000

Data Index: 494076 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1374792 (The Pile)

Max Activating Token Index: 16

Text #12

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2106. Min Act: -0.0000

Data Index: 868143 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1189273 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1329898 (The Pile)

Max Activating Token Index: 745

Text #15

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1829800 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1758984 (The Pile)

Max Activating Token Index: 950

Text #17

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1447204 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1937639 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 0.2521. Min Range: -0.2521

Max Act: 0.1883. Min Act: -0.0000

Data Index: 854213 (The Pile)

Max Activating Token Index: 625