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

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

Neuron 124 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.3255. Min Act: -0.0000

Data Index: 926066 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.3423. Min Act: -0.0000

Data Index: 80573 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1203126 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.3125. Min Act: -0.0000

Data Index: 773798 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1226810 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1540403 (Python Code)

Max Activating Token Index: 656

Text #6

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1384932 (Python Code)

Max Activating Token Index: 90

Text #7

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2722. Min Act: -0.0000

Data Index: 446549 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2125. Min Act: -0.0000

Data Index: 234780 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2681. Min Act: -0.0000

Data Index: 1595499 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1061769 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2493. Min Act: -0.0000

Data Index: 1513513 (Python Code)

Max Activating Token Index: 409

Text #12

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1487400 (Python Code)

Max Activating Token Index: 984

Text #13

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1509192 (Python Code)

Max Activating Token Index: 466

Text #14

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1143104 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2830. Min Act: -0.0000

Data Index: 54585 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1012446 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2459. Min Act: -0.0000

Data Index: 494608 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1076095 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.3498. Min Range: -0.3498

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1469690 (Python Code)

Max Activating Token Index: 276