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

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

Neuron 2460 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0785. Min Range: -4.0785

Max Act: 4.0785. Min Act: -0.0000

Data Index: 18007 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.6053. Min Act: -0.0000

Data Index: 520448 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.7247. Min Act: -0.0000

Data Index: 527065 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.4075. Min Act: -0.0000

Data Index: 275727 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.2677. Min Act: -0.0000

Data Index: 541271 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.2009. Min Act: -0.0000

Data Index: 1120364 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.1569. Min Act: -0.0000

Data Index: 523426 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.2630. Min Act: -0.0000

Data Index: 1199300 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.9244. Min Act: -0.0000

Data Index: 1247579 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.9230. Min Act: 0.0000

Data Index: 990642 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 4.0785. Min Range: -4.0785

Max Act: 3.0216. Min Act: 0.0001

Data Index: 591291 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.8642. Min Act: -0.0000

Data Index: 1054679 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.8558. Min Act: 0.0001

Data Index: 546240 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.8287. Min Act: -0.0000

Data Index: 309937 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.7923. Min Act: 0.0000

Data Index: 586400 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.9231. Min Act: -0.0000

Data Index: 1257107 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.6241. Min Act: -0.0000

Data Index: 258412 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.6110. Min Act: -0.0000

Data Index: 1247619 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.7603. Min Act: -0.0000

Data Index: 93354 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 4.0785. Min Range: -4.0785

Max Act: 2.7322. Min Act: -0.0000

Data Index: 934847 (C4 (Web Text))

Max Activating Token Index: 994