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

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

Neuron 653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.7894. Min Act: -0.0000

Data Index: 1475778 (Python Code)

Max Activating Token Index: 777

Text #1

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.4948. Min Act: -0.0000

Data Index: 1525734 (Python Code)

Max Activating Token Index: 465

Text #2

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.2883. Min Act: -0.0000

Data Index: 1494810 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.5067. Min Act: -0.0000

Data Index: 1607528 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.3103. Min Act: -0.0000

Data Index: 1411014 (Python Code)

Max Activating Token Index: 823

Text #5

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.4512. Min Act: -0.0000

Data Index: 1429805 (Python Code)

Max Activating Token Index: 678

Text #6

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.3370. Min Act: -0.0000

Data Index: 1374052 (Python Code)

Max Activating Token Index: 858

Text #7

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.1666. Min Act: -0.0000

Data Index: 1427071 (Python Code)

Max Activating Token Index: 591

Text #8

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.1255. Min Act: -0.0000

Data Index: 1495032 (Python Code)

Max Activating Token Index: 575

Text #9

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.0757. Min Act: -0.0000

Data Index: 1641203 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 2.7894. Min Range: -2.7894

Max Act: 1.7830. Min Act: -0.0000

Data Index: 1593336 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.0913. Min Act: -0.0000

Data Index: 1494306 (Python Code)

Max Activating Token Index: 124

Text #12

Max Range: 2.7894. Min Range: -2.7894

Max Act: 1.7624. Min Act: -0.0000

Data Index: 1566993 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 2.7894. Min Range: -2.7894

Max Act: 1.8402. Min Act: -0.0000

Data Index: 1441361 (Python Code)

Max Activating Token Index: 634

Text #14

Max Range: 2.7894. Min Range: -2.7894

Max Act: 1.9391. Min Act: -0.0000

Data Index: 1366359 (Python Code)

Max Activating Token Index: 567

Text #15

Max Range: 2.7894. Min Range: -2.7894

Max Act: 2.0492. Min Act: -0.0000

Data Index: 1381007 (Python Code)

Max Activating Token Index: 525

Text #16

Max Range: 2.7894. Min Range: -2.7894

Max Act: 1.9275. Min Act: -0.0000

Data Index: 1453213 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 2.7894. Min Range: -2.7894

Max Act: 1.8100. Min Act: -0.0000

Data Index: 1437838 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 2.7894. Min Range: -2.7894

Max Act: 1.9952. Min Act: -0.0000

Data Index: 1500685 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 2.7894. Min Range: -2.7894

Max Act: 1.6884. Min Act: -0.0000

Data Index: 1495491 (Python Code)

Max Activating Token Index: 354