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

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

Neuron 1840 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.9080. Min Act: -0.0000

Data Index: 1531123 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.4538. Min Act: -0.0000

Data Index: 1395842 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.5057. Min Act: -0.0000

Data Index: 1496901 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.4970. Min Act: -0.0000

Data Index: 1384954 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.4754. Min Act: -0.0000

Data Index: 1588634 (Python Code)

Max Activating Token Index: 452

Text #5

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.3218. Min Act: -0.0000

Data Index: 1564623 (Python Code)

Max Activating Token Index: 423

Text #6

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.2624. Min Act: -0.0000

Data Index: 1371688 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.3504. Min Act: -0.0000

Data Index: 1465456 (Python Code)

Max Activating Token Index: 379

Text #8

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1439277 (Python Code)

Max Activating Token Index: 395

Text #9

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1926. Min Act: -0.0000

Data Index: 1453515 (Python Code)

Max Activating Token Index: 1000

Text #10

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1366822 (Python Code)

Max Activating Token Index: 189

Text #11

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.2124. Min Act: -0.0000

Data Index: 1477168 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1979. Min Act: -0.0000

Data Index: 1568988 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.2285. Min Act: -0.0000

Data Index: 1633486 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1842. Min Act: -0.0000

Data Index: 1458751 (Python Code)

Max Activating Token Index: 478

Text #15

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1766. Min Act: -0.0000

Data Index: 1642199 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1640188 (Python Code)

Max Activating Token Index: 924

Text #17

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1451547 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1473. Min Act: -0.0000

Data Index: 1468660 (Python Code)

Max Activating Token Index: 108

Text #19

Max Range: 1.9080. Min Range: -1.9080

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1394033 (Python Code)

Max Activating Token Index: 900