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

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

Neuron 1825 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1418813 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7276. Min Act: -0.0000

Data Index: 1510033 (Python Code)

Max Activating Token Index: 387

Text #2

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1535479 (Python Code)

Max Activating Token Index: 300

Text #3

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1483541 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1513042 (Python Code)

Max Activating Token Index: 614

Text #5

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1379657 (Python Code)

Max Activating Token Index: 554

Text #6

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1475284 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1418088 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1561082 (Python Code)

Max Activating Token Index: 441

Text #9

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1390856 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1408393 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1410430 (Python Code)

Max Activating Token Index: 751

Text #12

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1394459 (Python Code)

Max Activating Token Index: 495

Text #13

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1480463 (Python Code)

Max Activating Token Index: 420

Text #14

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1531619 (Python Code)

Max Activating Token Index: 427

Text #15

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1376803 (Python Code)

Max Activating Token Index: 405

Text #16

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1546905 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1360296 (Python Code)

Max Activating Token Index: 636

Text #18

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1391812 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 0.7842. Min Range: -0.7842

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1627130 (Python Code)

Max Activating Token Index: 363