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

Dataset: The Pile

Neuron 4281 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: 3.8239. Min Range: -3.8239

Max Act: 3.7886. Min Act: -0.0000

Data Index: 1036663 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.3685. Min Act: -0.0000

Data Index: 1271289 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.8239. Min Act: -0.0000

Data Index: 1331330 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.6785. Min Act: -0.0000

Data Index: 376291 (The Pile)

Max Activating Token Index: 774

Text #4

Max Range: 3.8239. Min Range: -3.8239

Max Act: 2.9888. Min Act: -0.0000

Data Index: 1733903 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.1237. Min Act: -0.0000

Data Index: 1758345 (The Pile)

Max Activating Token Index: 960

Text #6

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.2293. Min Act: -0.0000

Data Index: 1983559 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.2225. Min Act: -0.0000

Data Index: 4567 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.1892. Min Act: -0.0000

Data Index: 722603 (The Pile)

Max Activating Token Index: 465

Text #9

Max Range: 3.8239. Min Range: -3.8239

Max Act: 2.8428. Min Act: -0.0000

Data Index: 150512 (The Pile)

Max Activating Token Index: 926

Text #10

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.2329. Min Act: -0.0000

Data Index: 912244 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.2247. Min Act: -0.0000

Data Index: 1651509 (The Pile)

Max Activating Token Index: 673

Text #12

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.2106. Min Act: -0.0000

Data Index: 1098362 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.0039. Min Act: -0.0000

Data Index: 204019 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.0340. Min Act: -0.0000

Data Index: 1679265 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.3112. Min Act: -0.0000

Data Index: 1844173 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.3164. Min Act: -0.0000

Data Index: 661363 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 3.8239. Min Range: -3.8239

Max Act: 2.8584. Min Act: -0.0000

Data Index: 1082729 (The Pile)

Max Activating Token Index: 517

Text #18

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.1646. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 3.8239. Min Range: -3.8239

Max Act: 3.1300. Min Act: -0.0000

Data Index: 978831 (The Pile)

Max Activating Token Index: 455