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

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

Neuron 3630 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.8017. Min Act: 0.0000

Data Index: 376785 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.7110. Min Act: -0.0000

Data Index: 128212 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.7185. Min Act: -0.0000

Data Index: 702528 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6598. Min Act: -0.0000

Data Index: 607281 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6610. Min Act: -0.0000

Data Index: 620396 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1246810 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6444. Min Act: -0.0000

Data Index: 363158 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6607. Min Act: -0.0000

Data Index: 217505 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6225. Min Act: -0.0000

Data Index: 242039 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1411 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1318359 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1283054 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5930. Min Act: -0.0000

Data Index: 775203 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.6249. Min Act: -0.0000

Data Index: 518716 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5958. Min Act: -0.0000

Data Index: 897176 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5727. Min Act: -0.0000

Data Index: 732360 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5609. Min Act: -0.0000

Data Index: 913926 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5835. Min Act: -0.0000

Data Index: 853857 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5580. Min Act: -0.0000

Data Index: 748492 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.8017. Min Range: -0.8017

Max Act: 0.5726. Min Act: -0.0000

Data Index: 422692 (C4 (Web Text))

Max Activating Token Index: 724