Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1344 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.8481. Min Act: -0.0000

Data Index: 451285 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6851. Min Act: -0.0000

Data Index: 391514 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5787. Min Act: -0.0000

Data Index: 369858 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6409. Min Act: -0.0000

Data Index: 390334 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5532. Min Act: -0.0000

Data Index: 149121 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1130396 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1293215 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5347. Min Act: -0.0000

Data Index: 262812 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6256. Min Act: -0.0000

Data Index: 730184 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5496. Min Act: -0.0000

Data Index: 788476 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5248. Min Act: -0.0000

Data Index: 667874 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5648. Min Act: -0.0000

Data Index: 225459 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5516. Min Act: -0.0000

Data Index: 271191 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.4805. Min Act: -0.0000

Data Index: 738899 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5379. Min Act: -0.0000

Data Index: 433126 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1106097 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5312. Min Act: -0.0000

Data Index: 124469 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1222299 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1013374 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5557. Min Act: -0.0000

Data Index: 550012 (C4 (Web Text))

Max Activating Token Index: 555