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

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

Neuron 4715 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: 0.5278. Min Range: -0.5278

Max Act: 0.5278. Min Act: -0.0002

Data Index: 589017 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.4757. Min Act: -0.0002

Data Index: 1223154 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.4583. Min Act: -0.0002

Data Index: 454157 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.4475. Min Act: -0.0002

Data Index: 274640 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.4204. Min Act: -0.0002

Data Index: 1318823 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.4195. Min Act: -0.0002

Data Index: 644802 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3749. Min Act: -0.0002

Data Index: 752312 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3860. Min Act: -0.0002

Data Index: 512004 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3912. Min Act: -0.0002

Data Index: 1085608 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3795. Min Act: -0.0002

Data Index: 1007805 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3788. Min Act: -0.0002

Data Index: 384659 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3817. Min Act: -0.0002

Data Index: 993586 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3767. Min Act: -0.0002

Data Index: 107322 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3412. Min Act: -0.0002

Data Index: 64072 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3658. Min Act: -0.0002

Data Index: 64822 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3575. Min Act: -0.0002

Data Index: 359866 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3629. Min Act: -0.0002

Data Index: 475769 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3466. Min Act: -0.0002

Data Index: 348569 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3587. Min Act: -0.0002

Data Index: 898816 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.5278. Min Range: -0.5278

Max Act: 0.3425. Min Act: -0.0002

Data Index: 345962 (C4 (Web Text))

Max Activating Token Index: 697