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

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

Neuron 483 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5536. Min Range: -6.5536

Max Act: 6.5536. Min Act: -0.0000

Data Index: 1376793 (Python Code)

Max Activating Token Index: 589

Text #1

Max Range: 6.5536. Min Range: -6.5536

Max Act: 5.6723. Min Act: -0.0000

Data Index: 1562600 (Python Code)

Max Activating Token Index: 887

Text #2

Max Range: 6.5536. Min Range: -6.5536

Max Act: 4.4174. Min Act: -0.0000

Data Index: 1651169 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 6.5536. Min Range: -6.5536

Max Act: 4.4446. Min Act: -0.0000

Data Index: 1642685 (Python Code)

Max Activating Token Index: 166

Text #4

Max Range: 6.5536. Min Range: -6.5536

Max Act: 4.3353. Min Act: -0.0000

Data Index: 1517955 (Python Code)

Max Activating Token Index: 91

Text #5

Max Range: 6.5536. Min Range: -6.5536

Max Act: 4.6274. Min Act: -0.0000

Data Index: 1633082 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 6.5536. Min Range: -6.5536

Max Act: 4.1682. Min Act: -0.0000

Data Index: 1429745 (Python Code)

Max Activating Token Index: 519

Text #7

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.9400. Min Act: -0.0000

Data Index: 1641805 (Python Code)

Max Activating Token Index: 540

Text #8

Max Range: 6.5536. Min Range: -6.5536

Max Act: 4.1997. Min Act: -0.0000

Data Index: 1621769 (Python Code)

Max Activating Token Index: 564

Text #9

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.4173. Min Act: -0.0000

Data Index: 1367414 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.8643. Min Act: -0.0000

Data Index: 1398442 (Python Code)

Max Activating Token Index: 449

Text #11

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.6731. Min Act: -0.0000

Data Index: 1519278 (Python Code)

Max Activating Token Index: 910

Text #12

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.1152. Min Act: -0.0000

Data Index: 1476171 (Python Code)

Max Activating Token Index: 847

Text #13

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.7033. Min Act: -0.0000

Data Index: 1560497 (Python Code)

Max Activating Token Index: 302

Text #14

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.6510. Min Act: -0.0000

Data Index: 1480310 (Python Code)

Max Activating Token Index: 207

Text #15

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.3304. Min Act: -0.0000

Data Index: 1492383 (Python Code)

Max Activating Token Index: 961

Text #16

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.6025. Min Act: -0.0000

Data Index: 726586 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.5109. Min Act: -0.0000

Data Index: 71881 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.4573. Min Act: -0.0000

Data Index: 1434416 (Python Code)

Max Activating Token Index: 1004

Text #19

Max Range: 6.5536. Min Range: -6.5536

Max Act: 3.4530. Min Act: -0.0000

Data Index: 1552686 (Python Code)

Max Activating Token Index: 629