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

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

Neuron 3282 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.5305. Min Act: -0.0000

Data Index: 698464 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.5621. Min Act: -0.0000

Data Index: 851206 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.4904. Min Act: -0.0000

Data Index: 11080 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.2944. Min Act: -0.0000

Data Index: 674145 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.3010. Min Act: -0.0000

Data Index: 621864 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.2204. Min Act: -0.0000

Data Index: 913320 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.1607. Min Act: -0.0000

Data Index: 422908 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.1242. Min Act: -0.0000

Data Index: 905159 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0491. Min Act: -0.0000

Data Index: 206843 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.1014. Min Act: -0.0000

Data Index: 405209 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0835. Min Act: -0.0000

Data Index: 466770 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0862. Min Act: -0.0000

Data Index: 21466 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0832. Min Act: -0.0000

Data Index: 263629 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0733. Min Act: 0.0000

Data Index: 376839 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1016332 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.9825. Min Act: -0.0000

Data Index: 535741 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1184482 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0000. Min Act: -0.0000

Data Index: 320496 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 1.5621. Min Range: -1.5621

Max Act: 1.0650. Min Act: -0.0000

Data Index: 651444 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.5621. Min Range: -1.5621

Max Act: 0.9357. Min Act: -0.0000

Data Index: 551570 (C4 (Web Text))

Max Activating Token Index: 732