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

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

Neuron 3209 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: 0.9481. Min Range: -0.9481

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1529449 (Python Code)

Max Activating Token Index: 1000

Text #1

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1475325 (Python Code)

Max Activating Token Index: 502

Text #2

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7744. Min Act: -0.0000

Data Index: 77259 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6996. Min Act: -0.0000

Data Index: 839711 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6648. Min Act: -0.0000

Data Index: 12056 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7680. Min Act: -0.0000

Data Index: 845563 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6559. Min Act: -0.0000

Data Index: 75321 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1572847 (Python Code)

Max Activating Token Index: 974

Text #8

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1609598 (Python Code)

Max Activating Token Index: 810

Text #9

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1434108 (Python Code)

Max Activating Token Index: 850

Text #10

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5981. Min Act: -0.0000

Data Index: 747904 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1343969 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.6029. Min Act: -0.0000

Data Index: 579342 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5462. Min Act: -0.0000

Data Index: 988327 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5925. Min Act: -0.0000

Data Index: 77054 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5172. Min Act: -0.0000

Data Index: 64404 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5453. Min Act: -0.0000

Data Index: 29665 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5503. Min Act: -0.0000

Data Index: 512846 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1187240 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.9481. Min Range: -0.9481

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1490409 (Python Code)

Max Activating Token Index: 489