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

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

Neuron 3111 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: 0.8015. Min Range: -0.8015

Max Act: 0.8015. Min Act: -0.0001

Data Index: 1025517 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6936. Min Act: -0.0001

Data Index: 157268 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1498524 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5617. Min Act: -0.0001

Data Index: 221406 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6085. Min Act: -0.0001

Data Index: 1626603 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5707. Min Act: -0.0001

Data Index: 1426340 (Python Code)

Max Activating Token Index: 338

Text #6

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5557. Min Act: -0.0001

Data Index: 1547039 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5531. Min Act: -0.0001

Data Index: 1527868 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5358. Min Act: -0.0001

Data Index: 1368973 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5171. Min Act: -0.0001

Data Index: 982175 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5349. Min Act: -0.0001

Data Index: 1620197 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5311. Min Act: -0.0001

Data Index: 1353265 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5308. Min Act: -0.0001

Data Index: 1460409 (Python Code)

Max Activating Token Index: 242

Text #13

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5426. Min Act: -0.0001

Data Index: 717119 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5128. Min Act: -0.0001

Data Index: 1493165 (Python Code)

Max Activating Token Index: 154

Text #15

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5084. Min Act: -0.0001

Data Index: 1549752 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5084. Min Act: -0.0001

Data Index: 607406 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.4853. Min Act: -0.0001

Data Index: 1399346 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.4704. Min Act: -0.0001

Data Index: 1468950 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.5076. Min Act: -0.0001

Data Index: 563201 (C4 (Web Text))

Max Activating Token Index: 801