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

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

Neuron 567 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: 0.8038. Min Range: -0.8038

Max Act: 0.8038. Min Act: -0.0001

Data Index: 14184 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.7333. Min Act: -0.0000

Data Index: 233553 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.7257. Min Act: -0.0001

Data Index: 1213972 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6836. Min Act: -0.0000

Data Index: 8688 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6786. Min Act: -0.0001

Data Index: 1353433 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6780. Min Act: -0.0001

Data Index: 413307 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6931. Min Act: -0.0001

Data Index: 190897 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6595. Min Act: -0.0001

Data Index: 692424 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6632. Min Act: -0.0001

Data Index: 1260373 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6562. Min Act: -0.0000

Data Index: 266867 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6560. Min Act: -0.0001

Data Index: 242110 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6736. Min Act: -0.0001

Data Index: 388049 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6539. Min Act: -0.0001

Data Index: 1065696 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6286. Min Act: -0.0001

Data Index: 409122 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6715. Min Act: -0.0001

Data Index: 692667 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6288. Min Act: -0.0001

Data Index: 1122324 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6470. Min Act: -0.0001

Data Index: 1185251 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6186. Min Act: -0.0001

Data Index: 729228 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6296. Min Act: -0.0001

Data Index: 256778 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.8038. Min Range: -0.8038

Max Act: 0.6299. Min Act: -0.0000

Data Index: 954912 (C4 (Web Text))

Max Activating Token Index: 799