Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1163 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5722. Min Act: -0.0000

Data Index: 261722 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5442. Min Act: -0.0000

Data Index: 566799 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.5024. Min Act: -0.0000

Data Index: 275902 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1337398 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4459. Min Act: -0.0000

Data Index: 483825 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1582083 (Python Code)

Max Activating Token Index: 450

Text #6

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4556. Min Act: -0.0000

Data Index: 550633 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1229084 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4206. Min Act: -0.0000

Data Index: 944056 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4159. Min Act: -0.0000

Data Index: 793601 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4099. Min Act: -0.0000

Data Index: 923498 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4004. Min Act: -0.0000

Data Index: 746163 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1470540 (Python Code)

Max Activating Token Index: 287

Text #13

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1227541 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4187. Min Act: -0.0000

Data Index: 679003 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3887. Min Act: -0.0000

Data Index: 265886 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4104. Min Act: -0.0000

Data Index: 727914 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.3735. Min Act: -0.0000

Data Index: 1624896 (Python Code)

Max Activating Token Index: 734

Text #18

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4215. Min Act: -0.0000

Data Index: 159102 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.5722. Min Range: -0.5722

Max Act: 0.4208. Min Act: -0.0000

Data Index: 396720 (C4 (Web Text))

Max Activating Token Index: 678