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

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

Neuron 4407 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1588752 (Python Code)

Max Activating Token Index: 193

Text #1

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4717. Min Act: -0.0000

Data Index: 1395343 (Python Code)

Max Activating Token Index: 782

Text #2

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1513056 (Python Code)

Max Activating Token Index: 656

Text #3

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4425. Min Act: -0.0000

Data Index: 1531385 (Python Code)

Max Activating Token Index: 354

Text #4

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4375. Min Act: -0.0000

Data Index: 1541107 (Python Code)

Max Activating Token Index: 893

Text #5

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1639388 (Python Code)

Max Activating Token Index: 830

Text #6

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1656155 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1404685 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1421038 (Python Code)

Max Activating Token Index: 423

Text #9

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1496090 (Python Code)

Max Activating Token Index: 909

Text #10

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1465014 (Python Code)

Max Activating Token Index: 358

Text #11

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1599621 (Python Code)

Max Activating Token Index: 766

Text #12

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1366436 (Python Code)

Max Activating Token Index: 584

Text #13

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1637420 (Python Code)

Max Activating Token Index: 423

Text #14

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1508718 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1365732 (Python Code)

Max Activating Token Index: 879

Text #16

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1627753 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1484699 (Python Code)

Max Activating Token Index: 205

Text #18

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1512376 (Python Code)

Max Activating Token Index: 697

Text #19

Max Range: 0.4805. Min Range: -0.4805

Max Act: 0.3877. Min Act: -0.0000

Data Index: 339579 (C4 (Web Text))

Max Activating Token Index: 768