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

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

Neuron 4765 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.6110. Min Act: -0.0002

Data Index: 1483643 (Python Code)

Max Activating Token Index: 982

Text #1

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.5365. Min Act: -0.0002

Data Index: 1605472 (Python Code)

Max Activating Token Index: 237

Text #2

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.6157. Min Act: -0.0002

Data Index: 1582724 (Python Code)

Max Activating Token Index: 545

Text #3

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.5776. Min Act: -0.0002

Data Index: 1421083 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.7318. Min Act: -0.0002

Data Index: 1458925 (Python Code)

Max Activating Token Index: 732

Text #5

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.6730. Min Act: -0.0002

Data Index: 1396372 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.5007. Min Act: -0.0002

Data Index: 1607428 (Python Code)

Max Activating Token Index: 490

Text #7

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.4736. Min Act: -0.0002

Data Index: 1545873 (Python Code)

Max Activating Token Index: 509

Text #8

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.3498. Min Act: -0.0002

Data Index: 1480227 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.5276. Min Act: -0.0002

Data Index: 1482944 (Python Code)

Max Activating Token Index: 882

Text #10

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.5697. Min Act: -0.0002

Data Index: 1554681 (Python Code)

Max Activating Token Index: 638

Text #11

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.6032. Min Act: -0.0002

Data Index: 1450657 (Python Code)

Max Activating Token Index: 780

Text #12

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.5885. Min Act: -0.0002

Data Index: 1534817 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.4160. Min Act: -0.0002

Data Index: 1418119 (Python Code)

Max Activating Token Index: 935

Text #14

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.5455. Min Act: -0.0002

Data Index: 1464582 (Python Code)

Max Activating Token Index: 972

Text #15

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.3209. Min Act: -0.0002

Data Index: 1603523 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.3739. Min Act: -0.0002

Data Index: 1549425 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.4349. Min Act: -0.0002

Data Index: 1482344 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.2801. Min Act: -0.0002

Data Index: 1536397 (Python Code)

Max Activating Token Index: 755

Text #19

Max Range: 1.7318. Min Range: -1.7318

Max Act: 1.4071. Min Act: -0.0002

Data Index: 1526335 (Python Code)

Max Activating Token Index: 653