Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1326 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.6278. Min Act: -0.0000

Data Index: 71303 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.5785. Min Act: -0.0000

Data Index: 982048 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.5343. Min Act: -0.0000

Data Index: 406673 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4995. Min Act: -0.0000

Data Index: 739939 (The Pile)

Max Activating Token Index: 897

Text #4

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4976. Min Act: -0.0000

Data Index: 484243 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1558595 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4563. Min Act: -0.0000

Data Index: 1434833 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4579. Min Act: -0.0000

Data Index: 861957 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4522. Min Act: -0.0000

Data Index: 554199 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4703. Min Act: -0.0000

Data Index: 926865 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1370381 (The Pile)

Max Activating Token Index: 588

Text #11

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1534151 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1189519 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1761050 (The Pile)

Max Activating Token Index: 398

Text #14

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4721. Min Act: -0.0000

Data Index: 1233547 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1277992 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4112. Min Act: -0.0000

Data Index: 418955 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1092956 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1658739 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1846270 (The Pile)

Max Activating Token Index: 927