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

Dataset: The Pile

Neuron 2530 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: 1.0133. Min Range: -1.0133

Max Act: 1.0133. Min Act: -0.0000

Data Index: 182096 (The Pile)

Max Activating Token Index: 395

Text #1

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9084. Min Act: -0.0000

Data Index: 199390 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8466. Min Act: -0.0000

Data Index: 870398 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8135. Min Act: -0.0000

Data Index: 850627 (The Pile)

Max Activating Token Index: 351

Text #4

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7820. Min Act: -0.0000

Data Index: 883484 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.6992. Min Act: -0.0000

Data Index: 853633 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1738966 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1827386 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.6390. Min Act: -0.0000

Data Index: 499213 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.6711. Min Act: -0.0000

Data Index: 175339 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1541079 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7205. Min Act: -0.0000

Data Index: 732555 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1539139 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1129324 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1062391 (The Pile)

Max Activating Token Index: 530

Text #15

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.5594. Min Act: -0.0000

Data Index: 208115 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.5911. Min Act: -0.0000

Data Index: 128985 (The Pile)

Max Activating Token Index: 731

Text #17

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1073226 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.5625. Min Act: -0.0000

Data Index: 1908491 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.5742. Min Act: -0.0000

Data Index: 745482 (The Pile)

Max Activating Token Index: 751