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

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

Neuron 4910 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.6094. Min Act: -0.0000

Data Index: 259991 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.6998. Min Act: -0.0000

Data Index: 959261 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.6199. Min Act: -0.0000

Data Index: 932736 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.5744. Min Act: -0.0000

Data Index: 201054 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.6200. Min Act: -0.0000

Data Index: 753990 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.5374. Min Act: -0.0000

Data Index: 619018 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.5386. Min Act: -0.0000

Data Index: 28660 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1180683 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.5214. Min Act: -0.0000

Data Index: 567931 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4782. Min Act: -0.0000

Data Index: 260446 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4934. Min Act: -0.0000

Data Index: 920161 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4856. Min Act: -0.0000

Data Index: 478677 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4778. Min Act: -0.0000

Data Index: 782418 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4911. Min Act: -0.0000

Data Index: 180589 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4722. Min Act: -0.0000

Data Index: 229557 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1359230 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4427. Min Act: -0.0000

Data Index: 407982 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4460. Min Act: -0.0000

Data Index: 133945 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4401. Min Act: -0.0000

Data Index: 414906 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.6998. Min Range: -0.6998

Max Act: 0.4234. Min Act: -0.0000

Data Index: 273251 (C4 (Web Text))

Max Activating Token Index: 958