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

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

Neuron 4501 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7966. Min Act: -0.0000

Data Index: 1490875 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.8692. Min Act: -0.0000

Data Index: 1602107 (Python Code)

Max Activating Token Index: 270

Text #2

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7979. Min Act: -0.0000

Data Index: 1487479 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7837. Min Act: -0.0000

Data Index: 1486636 (Python Code)

Max Activating Token Index: 1016

Text #4

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7608. Min Act: -0.0000

Data Index: 1524235 (Python Code)

Max Activating Token Index: 569

Text #5

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1482789 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.5830. Min Act: -0.0000

Data Index: 1590667 (Python Code)

Max Activating Token Index: 265

Text #7

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.7044. Min Act: -0.0000

Data Index: 1442192 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.4300. Min Act: -0.0000

Data Index: 1547271 (Python Code)

Max Activating Token Index: 1015

Text #9

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.4432. Min Act: -0.0000

Data Index: 1470613 (Python Code)

Max Activating Token Index: 663

Text #10

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1497751 (Python Code)

Max Activating Token Index: 127

Text #11

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1396206 (Python Code)

Max Activating Token Index: 955

Text #12

Max Range: 1.8692. Min Range: -1.8692

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1436525 (Python Code)

Max Activating Token Index: 459

Text #13

Max Range: 1.8692. Min Range: -1.8692

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1518959 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 1.8692. Min Range: -1.8692

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1646876 (Python Code)

Max Activating Token Index: 286

Text #15

Max Range: 1.8692. Min Range: -1.8692

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1582412 (Python Code)

Max Activating Token Index: 381

Text #16

Max Range: 1.8692. Min Range: -1.8692

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1633675 (Python Code)

Max Activating Token Index: 500

Text #17

Max Range: 1.8692. Min Range: -1.8692

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1604507 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 1.8692. Min Range: -1.8692

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1487513 (Python Code)

Max Activating Token Index: 1006

Text #19

Max Range: 1.8692. Min Range: -1.8692

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1410655 (Python Code)

Max Activating Token Index: 331