Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.8812. Min Act: -0.0001

Data Index: 1527838 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.7964. Min Act: -0.0001

Data Index: 1381370 (Python Code)

Max Activating Token Index: 559

Text #2

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.7608. Min Act: -0.0001

Data Index: 725014 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6976. Min Act: -0.0001

Data Index: 1548791 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6834. Min Act: -0.0001

Data Index: 1381726 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1395237 (Python Code)

Max Activating Token Index: 765

Text #6

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6889. Min Act: -0.0001

Data Index: 1619318 (Python Code)

Max Activating Token Index: 716

Text #7

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.7068. Min Act: -0.0001

Data Index: 124767 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6983. Min Act: -0.0001

Data Index: 478185 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.7053. Min Act: -0.0001

Data Index: 1424225 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6778. Min Act: -0.0001

Data Index: 371289 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6309. Min Act: -0.0001

Data Index: 958566 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6549. Min Act: -0.0001

Data Index: 1239887 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6122. Min Act: -0.0001

Data Index: 1487931 (Python Code)

Max Activating Token Index: 656

Text #14

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6004. Min Act: -0.0001

Data Index: 952549 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6317. Min Act: -0.0001

Data Index: 1416531 (Python Code)

Max Activating Token Index: 365

Text #16

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6087. Min Act: -0.0001

Data Index: 810523 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.5867. Min Act: -0.0001

Data Index: 1095569 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6143. Min Act: -0.0001

Data Index: 674897 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.8812. Min Range: -0.8812

Max Act: 0.6304. Min Act: -0.0001

Data Index: 489611 (C4 (Web Text))

Max Activating Token Index: 967