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

Dataset: The Pile

Neuron 4007 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3457. Min Range: -3.3457

Max Act: 3.2418. Min Act: -0.0000

Data Index: 1317237 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.9135. Min Act: -0.0000

Data Index: 1118602 (The Pile)

Max Activating Token Index: 771

Text #2

Max Range: 3.3457. Min Range: -3.3457

Max Act: 3.1705. Min Act: -0.0000

Data Index: 153478 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 3.3457. Min Range: -3.3457

Max Act: 3.0878. Min Act: -0.0000

Data Index: 60580 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 3.3457. Min Range: -3.3457

Max Act: 3.2417. Min Act: -0.0000

Data Index: 1283122 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.9477. Min Act: -0.0000

Data Index: 1381653 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 3.3457. Min Range: -3.3457

Max Act: 3.2194. Min Act: -0.0000

Data Index: 58621 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 3.3457. Min Range: -3.3457

Max Act: 3.3457. Min Act: -0.0000

Data Index: 96298 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 3.3457. Min Range: -3.3457

Max Act: 3.0806. Min Act: -0.0000

Data Index: 1035105 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 3.3457. Min Range: -3.3457

Max Act: 3.0643. Min Act: -0.0000

Data Index: 915214 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.7416. Min Act: -0.0000

Data Index: 924198 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.8451. Min Act: -0.0000

Data Index: 395345 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.9495. Min Act: -0.0000

Data Index: 36826 (The Pile)

Max Activating Token Index: 715

Text #13

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.7776. Min Act: -0.0000

Data Index: 1461730 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.7159. Min Act: -0.0000

Data Index: 1877638 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.5972. Min Act: -0.0000

Data Index: 1660455 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.7219. Min Act: -0.0000

Data Index: 1446207 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.5609. Min Act: -0.0000

Data Index: 1613919 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.5217. Min Act: -0.0000

Data Index: 1178301 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 3.3457. Min Range: -3.3457

Max Act: 2.6233. Min Act: -0.0000

Data Index: 393403 (The Pile)

Max Activating Token Index: 756