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

Dataset: The Pile

Neuron 4179 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: 0.8828. Min Range: -0.8828

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1198302 (The Pile)

Max Activating Token Index: 234

Text #1

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.8191. Min Act: -0.0000

Data Index: 684655 (The Pile)

Max Activating Token Index: 558

Text #2

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.8163. Min Act: -0.0000

Data Index: 850153 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7780. Min Act: -0.0000

Data Index: 584483 (The Pile)

Max Activating Token Index: 457

Text #4

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7372. Min Act: -0.0000

Data Index: 61485 (The Pile)

Max Activating Token Index: 683

Text #5

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.7806. Min Act: -0.0000

Data Index: 329196 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1316062 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6755. Min Act: -0.0000

Data Index: 857898 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6229. Min Act: -0.0000

Data Index: 22346 (The Pile)

Max Activating Token Index: 706

Text #9

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1279963 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6393. Min Act: -0.0000

Data Index: 306017 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1864338 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1123553 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6223. Min Act: -0.0000

Data Index: 946303 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1525956 (The Pile)

Max Activating Token Index: 959

Text #15

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6397. Min Act: -0.0000

Data Index: 422263 (The Pile)

Max Activating Token Index: 896

Text #16

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6012. Min Act: -0.0000

Data Index: 299360 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1272684 (The Pile)

Max Activating Token Index: 391

Text #18

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5272. Min Act: -0.0000

Data Index: 181132 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 0.8828. Min Range: -0.8828

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1444563 (The Pile)

Max Activating Token Index: 553