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

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

Neuron 2596 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.7798. Min Act: -0.0000

Data Index: 272103 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.7537. Min Act: -0.0000

Data Index: 310995 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.6809. Min Act: -0.0000

Data Index: 1325287 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.6651. Min Act: -0.0000

Data Index: 1022060 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5542. Min Act: -0.0000

Data Index: 1562269 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5315. Min Act: -0.0000

Data Index: 10185 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5226. Min Act: -0.0000

Data Index: 1469958 (Python Code)

Max Activating Token Index: 412

Text #7

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5947. Min Act: -0.0000

Data Index: 1260272 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5738. Min Act: -0.0000

Data Index: 843335 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1423645 (Python Code)

Max Activating Token Index: 385

Text #10

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5530. Min Act: -0.0000

Data Index: 1529391 (Python Code)

Max Activating Token Index: 784

Text #11

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.4048. Min Act: -0.0000

Data Index: 789468 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3955. Min Act: -0.0000

Data Index: 1522441 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.4348. Min Act: -0.0000

Data Index: 144037 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.4323. Min Act: -0.0000

Data Index: 1584983 (Python Code)

Max Activating Token Index: 573

Text #15

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3625. Min Act: -0.0000

Data Index: 845472 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.4344. Min Act: -0.0000

Data Index: 729244 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3105. Min Act: -0.0000

Data Index: 1420579 (Python Code)

Max Activating Token Index: 497

Text #18

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.2486. Min Act: -0.0000

Data Index: 1197698 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3301. Min Act: -0.0000

Data Index: 518322 (C4 (Web Text))

Max Activating Token Index: 743