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

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

Neuron 2402 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.2423. Min Act: -0.0000

Data Index: 47365 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.2124. Min Act: -0.0000

Data Index: 147856 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1400223 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1360737 (Python Code)

Max Activating Token Index: 135

Text #4

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1553475 (Python Code)

Max Activating Token Index: 666

Text #5

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0441. Min Act: -0.0000

Data Index: 1655070 (Python Code)

Max Activating Token Index: 419

Text #6

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1552602 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1406469 (Python Code)

Max Activating Token Index: 486

Text #8

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1466255 (Python Code)

Max Activating Token Index: 481

Text #9

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1398534 (Python Code)

Max Activating Token Index: 822

Text #10

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1600030 (Python Code)

Max Activating Token Index: 62

Text #11

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1432039 (Python Code)

Max Activating Token Index: 822

Text #12

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0492. Min Act: -0.0000

Data Index: 1593940 (Python Code)

Max Activating Token Index: 166

Text #13

Max Range: 1.2423. Min Range: -1.2423

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1312185 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1635765 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1635030 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1369522 (Python Code)

Max Activating Token Index: 561

Text #17

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9782. Min Act: -0.0000

Data Index: 219018 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1431625 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 1.2423. Min Range: -1.2423

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1390116 (Python Code)

Max Activating Token Index: 820