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

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

Neuron 840 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1626477 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1611070 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1520221 (Python Code)

Max Activating Token Index: 574

Text #3

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1250662 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1442638 (Python Code)

Max Activating Token Index: 501

Text #5

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1158440 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1643947 (Python Code)

Max Activating Token Index: 979

Text #7

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1471908 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1609416 (Python Code)

Max Activating Token Index: 969

Text #9

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3942. Min Act: -0.0000

Data Index: 1553655 (Python Code)

Max Activating Token Index: 437

Text #10

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1366649 (Python Code)

Max Activating Token Index: 611

Text #11

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1532111 (Python Code)

Max Activating Token Index: 601

Text #12

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1640801 (Python Code)

Max Activating Token Index: 755

Text #13

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1429436 (Python Code)

Max Activating Token Index: 803

Text #14

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1647604 (Python Code)

Max Activating Token Index: 778

Text #15

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1491540 (Python Code)

Max Activating Token Index: 981

Text #16

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1503895 (Python Code)

Max Activating Token Index: 666

Text #17

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1646779 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1434440 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 0.5423. Min Range: -0.5423

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1518338 (Python Code)

Max Activating Token Index: 480