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

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

Neuron 2453 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: 0.7501. Min Range: -0.7501

Max Act: 0.7501. Min Act: 0.0000

Data Index: 409667 (C4 (Web Text))

Max Activating Token Index: 663

Text #1

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.6860. Min Act: -0.0000

Data Index: 233933 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.6086. Min Act: -0.0000

Data Index: 327693 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.6160. Min Act: -0.0000

Data Index: 8346 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5906. Min Act: -0.0000

Data Index: 470387 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5252. Min Act: -0.0000

Data Index: 827089 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1325075 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4806. Min Act: -0.0000

Data Index: 779124 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1197665 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1091729 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4872. Min Act: -0.0000

Data Index: 655259 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4662. Min Act: -0.0000

Data Index: 284274 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4793. Min Act: -0.0000

Data Index: 442279 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4869. Min Act: -0.0000

Data Index: 799746 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1238510 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1301367 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4687. Min Act: -0.0000

Data Index: 249957 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4703. Min Act: -0.0000

Data Index: 978958 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4796. Min Act: -0.0000

Data Index: 768667 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.7501. Min Range: -0.7501

Max Act: 0.4789. Min Act: 0.0000

Data Index: 1183250 (C4 (Web Text))

Max Activating Token Index: 864