Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4928 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.9055. Min Act: -0.0000

Data Index: 453988 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.9689. Min Act: -0.0000

Data Index: 1506118 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.8308. Min Act: 0.0000

Data Index: 307544 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.8452. Min Act: 0.0000

Data Index: 180422 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.5817. Min Act: -0.0000

Data Index: 1034955 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.5742. Min Act: -0.0000

Data Index: 982651 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.4596. Min Act: 0.0001

Data Index: 589986 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.5345. Min Act: -0.0000

Data Index: 427244 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.5201. Min Act: -0.0000

Data Index: 842506 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.6024. Min Act: -0.0000

Data Index: 468471 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.5141. Min Act: -0.0000

Data Index: 430211 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.4644. Min Act: -0.0000

Data Index: 323467 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.4903. Min Act: 0.0000

Data Index: 602971 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.4016. Min Act: -0.0000

Data Index: 579239 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.4849. Min Act: -0.0000

Data Index: 57661 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.4696. Min Act: -0.0000

Data Index: 472389 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.4389. Min Act: -0.0000

Data Index: 716853 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.3329. Min Act: 0.0000

Data Index: 868118 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.4847. Min Act: -0.0000

Data Index: 365796 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 1.9689. Min Range: -1.9689

Max Act: 1.3314. Min Act: -0.0000

Data Index: 1228524 (C4 (Web Text))

Max Activating Token Index: 211