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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3351 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.0971. Min Act: -0.0000

Data Index: 1521509 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.2110. Min Act: -0.0000

Data Index: 1447052 (Python Code)

Max Activating Token Index: 874

Text #2

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.1476. Min Act: -0.0000

Data Index: 1491223 (Python Code)

Max Activating Token Index: 355

Text #3

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.7590. Min Act: -0.0000

Data Index: 17705 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.0937. Min Act: -0.0000

Data Index: 1385898 (Python Code)

Max Activating Token Index: 515

Text #5

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.2042. Min Act: -0.0000

Data Index: 1648814 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.9706. Min Act: -0.0000

Data Index: 244461 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.0839. Min Act: -0.0000

Data Index: 1537274 (Python Code)

Max Activating Token Index: 830

Text #8

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.0404. Min Act: -0.0000

Data Index: 1400039 (Python Code)

Max Activating Token Index: 634

Text #9

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.9298. Min Act: -0.0000

Data Index: 1518479 (Python Code)

Max Activating Token Index: 432

Text #10

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.4428. Min Act: -0.0000

Data Index: 27924 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.0230. Min Act: -0.0000

Data Index: 50406 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.9160. Min Act: -0.0000

Data Index: 1112960 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.0217. Min Act: -0.0000

Data Index: 1556824 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.0006. Min Act: -0.0000

Data Index: 1592357 (Python Code)

Max Activating Token Index: 668

Text #15

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.9690. Min Act: -0.0000

Data Index: 713157 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.9447. Min Act: -0.0000

Data Index: 1641395 (Python Code)

Max Activating Token Index: 507

Text #17

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.6144. Min Act: -0.0000

Data Index: 636064 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 2.2110. Min Range: -2.2110

Max Act: 2.0295. Min Act: -0.0000

Data Index: 147019 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 2.2110. Min Range: -2.2110

Max Act: 1.7790. Min Act: -0.0000

Data Index: 52826 (C4 (Web Text))

Max Activating Token Index: 692