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

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

Neuron 2686 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3590. Min Act: -0.0001

Data Index: 38649 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2957. Min Act: -0.0001

Data Index: 1568341 (Python Code)

Max Activating Token Index: 211

Text #2

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3074. Min Act: -0.0001

Data Index: 692259 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3195. Min Act: -0.0001

Data Index: 557007 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1046617 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3072. Min Act: -0.0001

Data Index: 27223 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2979. Min Act: -0.0001

Data Index: 709493 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2968. Min Act: -0.0001

Data Index: 790459 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2869. Min Act: -0.0001

Data Index: 155787 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2958. Min Act: -0.0001

Data Index: 780411 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.3029. Min Act: -0.0001

Data Index: 863751 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2812. Min Act: -0.0001

Data Index: 1298056 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2789. Min Act: -0.0001

Data Index: 559059 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2928. Min Act: -0.0001

Data Index: 1076680 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2850. Min Act: -0.0001

Data Index: 44104 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2739. Min Act: -0.0001

Data Index: 449884 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2884. Min Act: -0.0001

Data Index: 683164 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2840. Min Act: -0.0001

Data Index: 53464 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2834. Min Act: -0.0001

Data Index: 1429442 (Python Code)

Max Activating Token Index: 488

Text #19

Max Range: 0.3590. Min Range: -0.3590

Max Act: 0.2771. Min Act: -0.0001

Data Index: 1167997 (C4 (Web Text))

Max Activating Token Index: 845