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

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

Neuron 650 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0481. Min Act: -0.0002

Data Index: 191041 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1084588 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1356017 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0410. Min Act: -0.0002

Data Index: 861703 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0403. Min Act: -0.0002

Data Index: 860039 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0395. Min Act: -0.0002

Data Index: 228241 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0401. Min Act: -0.0002

Data Index: 807741 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0383. Min Act: -0.0002

Data Index: 789775 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0391. Min Act: -0.0002

Data Index: 529010 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0363. Min Act: -0.0002

Data Index: 232738 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0355. Min Act: -0.0002

Data Index: 817877 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0354. Min Act: -0.0002

Data Index: 792439 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0357. Min Act: -0.0002

Data Index: 767396 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0343. Min Act: -0.0002

Data Index: 460600 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0350. Min Act: -0.0002

Data Index: 144515 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1177691 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0347. Min Act: -0.0002

Data Index: 933061 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0348. Min Act: -0.0002

Data Index: 693152 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0340. Min Act: -0.0002

Data Index: 205563 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0342. Min Act: -0.0002

Data Index: 834215 (C4 (Web Text))

Max Activating Token Index: 800