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

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

Neuron 4427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1031. Min Range: -1.1031

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1634422 (Python Code)

Max Activating Token Index: 342

Text #1

Max Range: 1.1031. Min Range: -1.1031

Max Act: 1.0793. Min Act: -0.0000

Data Index: 1590890 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1647511 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 1.1031. Min Range: -1.1031

Max Act: 1.0280. Min Act: -0.0000

Data Index: 1622801 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1651757 (Python Code)

Max Activating Token Index: 582

Text #5

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1643129 (Python Code)

Max Activating Token Index: 183

Text #6

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1442604 (Python Code)

Max Activating Token Index: 901

Text #7

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1602799 (Python Code)

Max Activating Token Index: 910

Text #8

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1470248 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1362322 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1460457 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1502655 (Python Code)

Max Activating Token Index: 458

Text #12

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1624762 (Python Code)

Max Activating Token Index: 690

Text #13

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1447889 (Python Code)

Max Activating Token Index: 787

Text #14

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1631853 (Python Code)

Max Activating Token Index: 278

Text #15

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1631186 (Python Code)

Max Activating Token Index: 628

Text #16

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1374779 (Python Code)

Max Activating Token Index: 288

Text #17

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1421633 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1377574 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 1.1031. Min Range: -1.1031

Max Act: 0.7525. Min Act: -0.0000

Data Index: 1428913 (Python Code)

Max Activating Token Index: 397