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

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

Neuron 5899 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: 5.2308. Min Range: -5.2308

Max Act: 5.2308. Min Act: -0.0000

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.5514. Min Act: -0.0000

Data Index: 1346308 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.6716. Min Act: -0.0000

Data Index: 440251 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.9693. Min Act: -0.0000

Data Index: 1047021 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.5253. Min Act: -0.0000

Data Index: 519356 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.3767. Min Act: -0.0000

Data Index: 302986 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.2527. Min Act: -0.0000

Data Index: 929756 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.1266. Min Act: -0.0000

Data Index: 528482 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.3354. Min Act: -0.0000

Data Index: 1174192 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.1965. Min Act: -0.0000

Data Index: 44396 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.0832. Min Act: -0.0000

Data Index: 32820 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 5.2308. Min Range: -5.2308

Max Act: 4.0729. Min Act: -0.0000

Data Index: 735574 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 5.2308. Min Range: -5.2308

Max Act: 3.7263. Min Act: -0.0000

Data Index: 731784 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 5.2308. Min Range: -5.2308

Max Act: 3.8212. Min Act: -0.0000

Data Index: 735076 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 5.2308. Min Range: -5.2308

Max Act: 3.8902. Min Act: -0.0000

Data Index: 752333 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 5.2308. Min Range: -5.2308

Max Act: 3.7117. Min Act: -0.0000

Data Index: 496073 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 5.2308. Min Range: -5.2308

Max Act: 3.9043. Min Act: -0.0000

Data Index: 472699 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 5.2308. Min Range: -5.2308

Max Act: 3.3921. Min Act: -0.0000

Data Index: 114626 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 5.2308. Min Range: -5.2308

Max Act: 3.5969. Min Act: -0.0000

Data Index: 707414 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 5.2308. Min Range: -5.2308

Max Act: 3.5116. Min Act: -0.0000

Data Index: 569463 (C4 (Web Text))

Max Activating Token Index: 428