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

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

Neuron 2345 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.1463. Min Act: -0.0000

Data Index: 246699 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.1463. Min Range: -1.1463

Max Act: 1.0700. Min Act: -0.0000

Data Index: 974439 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1438625 (Python Code)

Max Activating Token Index: 662

Text #3

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9494. Min Act: -0.0000

Data Index: 232934 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.9643. Min Act: -0.0000

Data Index: 1086528 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8635. Min Act: -0.0000

Data Index: 418236 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8419. Min Act: -0.0000

Data Index: 1581011 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7946. Min Act: -0.0000

Data Index: 81273 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1383737 (Python Code)

Max Activating Token Index: 805

Text #9

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1329504 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7935. Min Act: -0.0000

Data Index: 110457 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7686. Min Act: -0.0000

Data Index: 69293 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1247776 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7477. Min Act: -0.0000

Data Index: 838572 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7786. Min Act: -0.0000

Data Index: 438354 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1439280 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1457611 (Python Code)

Max Activating Token Index: 594

Text #17

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1554896 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1627087 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 1.1463. Min Range: -1.1463

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1643392 (Python Code)

Max Activating Token Index: 7