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

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

Neuron 3951 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2521. Min Range: -2.2521

Max Act: 2.2521. Min Act: -0.0000

Data Index: 1491406 (Python Code)

Max Activating Token Index: 615

Text #1

Max Range: 2.2521. Min Range: -2.2521

Max Act: 2.1156. Min Act: -0.0000

Data Index: 1494346 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 2.2521. Min Range: -2.2521

Max Act: 1.9631. Min Act: -0.0000

Data Index: 1533166 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 2.2521. Min Range: -2.2521

Max Act: 1.8662. Min Act: -0.0000

Data Index: 1536214 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 2.2521. Min Range: -2.2521

Max Act: 1.4188. Min Act: -0.0000

Data Index: 1584909 (Python Code)

Max Activating Token Index: 959

Text #5

Max Range: 2.2521. Min Range: -2.2521

Max Act: 1.4150. Min Act: -0.0000

Data Index: 1396907 (Python Code)

Max Activating Token Index: 522

Text #6

Max Range: 2.2521. Min Range: -2.2521

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1382163 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 2.2521. Min Range: -2.2521

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1557905 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1433739 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 2.2521. Min Range: -2.2521

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1567925 (Python Code)

Max Activating Token Index: 625

Text #10

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.9050. Min Act: -0.0001

Data Index: 1455950 (Python Code)

Max Activating Token Index: 676

Text #11

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1514947 (Python Code)

Max Activating Token Index: 45

Text #12

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1478224 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1496011 (Python Code)

Max Activating Token Index: 820

Text #14

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1550011 (Python Code)

Max Activating Token Index: 678

Text #15

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1470995 (Python Code)

Max Activating Token Index: 806

Text #16

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1578451 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.6034. Min Act: -0.0000

Data Index: 1589458 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1410016 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 2.2521. Min Range: -2.2521

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1469994 (Python Code)

Max Activating Token Index: 265