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

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

Neuron 3220 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.4217. Min Act: -0.0001

Data Index: 1555234 (Python Code)

Max Activating Token Index: 153

Text #1

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.4021. Min Act: -0.0000

Data Index: 622417 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3646. Min Act: -0.0001

Data Index: 1472772 (Python Code)

Max Activating Token Index: 804

Text #3

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3248. Min Act: -0.0001

Data Index: 1433520 (Python Code)

Max Activating Token Index: 434

Text #4

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1485770 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2792. Min Act: -0.0001

Data Index: 1390787 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3082. Min Act: -0.0001

Data Index: 1365857 (Python Code)

Max Activating Token Index: 317

Text #7

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2948. Min Act: -0.0001

Data Index: 1648931 (Python Code)

Max Activating Token Index: 876

Text #8

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2834. Min Act: -0.0001

Data Index: 1528581 (Python Code)

Max Activating Token Index: 136

Text #9

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.3027. Min Act: -0.0001

Data Index: 1627405 (Python Code)

Max Activating Token Index: 771

Text #10

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2934. Min Act: -0.0001

Data Index: 1381744 (Python Code)

Max Activating Token Index: 496

Text #11

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1386082 (Python Code)

Max Activating Token Index: 858

Text #12

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2748. Min Act: -0.0001

Data Index: 1486389 (Python Code)

Max Activating Token Index: 1020

Text #13

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2829. Min Act: -0.0001

Data Index: 1389786 (Python Code)

Max Activating Token Index: 188

Text #14

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2647. Min Act: -0.0001

Data Index: 1551698 (Python Code)

Max Activating Token Index: 222

Text #15

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2807. Min Act: -0.0001

Data Index: 1506413 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2979. Min Act: -0.0001

Data Index: 1372753 (Python Code)

Max Activating Token Index: 599

Text #17

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2865. Min Act: -0.0000

Data Index: 460863 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2836. Min Act: -0.0001

Data Index: 1654346 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 0.4217. Min Range: -0.4217

Max Act: 0.2740. Min Act: -0.0001

Data Index: 1657004 (Python Code)

Max Activating Token Index: 1001