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

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

Neuron 607 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5679. Min Range: -3.5679

Max Act: 3.5679. Min Act: -0.0000

Data Index: 1387816 (Python Code)

Max Activating Token Index: 887

Text #1

Max Range: 3.5679. Min Range: -3.5679

Max Act: 3.2433. Min Act: -0.0000

Data Index: 1619283 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.8708. Min Act: -0.0000

Data Index: 1454216 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.9557. Min Act: -0.0001

Data Index: 1473189 (Python Code)

Max Activating Token Index: 55

Text #4

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.4577. Min Act: -0.0000

Data Index: 1604725 (Python Code)

Max Activating Token Index: 685

Text #5

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.5634. Min Act: -0.0001

Data Index: 1442176 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.6443. Min Act: -0.0000

Data Index: 1515282 (Python Code)

Max Activating Token Index: 957

Text #7

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.4419. Min Act: -0.0000

Data Index: 1438667 (Python Code)

Max Activating Token Index: 923

Text #8

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.2589. Min Act: -0.0000

Data Index: 1431557 (Python Code)

Max Activating Token Index: 884

Text #9

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.2098. Min Act: -0.0000

Data Index: 1366798 (Python Code)

Max Activating Token Index: 816

Text #10

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.4738. Min Act: -0.0001

Data Index: 1468346 (Python Code)

Max Activating Token Index: 78

Text #11

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.6156. Min Act: -0.0000

Data Index: 1609768 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.4284. Min Act: -0.0000

Data Index: 1527498 (Python Code)

Max Activating Token Index: 583

Text #13

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.0019. Min Act: -0.0000

Data Index: 1428666 (Python Code)

Max Activating Token Index: 676

Text #14

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.4478. Min Act: -0.0000

Data Index: 1546675 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.4301. Min Act: -0.0000

Data Index: 1506637 (Python Code)

Max Activating Token Index: 918

Text #16

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.5405. Min Act: -0.0000

Data Index: 1570908 (Python Code)

Max Activating Token Index: 818

Text #17

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.2666. Min Act: -0.0001

Data Index: 1385537 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.5205. Min Act: -0.0000

Data Index: 1378365 (Python Code)

Max Activating Token Index: 818

Text #19

Max Range: 3.5679. Min Range: -3.5679

Max Act: 2.5029. Min Act: -0.0000

Data Index: 1364847 (Python Code)

Max Activating Token Index: 1015