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

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

Neuron 4801 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5867. Min Range: -1.5867

Max Act: 1.5867. Min Act: -0.0000

Data Index: 771065 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 1.5867. Min Range: -1.5867

Max Act: 1.3581. Min Act: -0.0000

Data Index: 787762 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.5867. Min Range: -1.5867

Max Act: 1.3525. Min Act: -0.0000

Data Index: 1012456 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.5867. Min Range: -1.5867

Max Act: 1.2824. Min Act: -0.0000

Data Index: 845648 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 1.5867. Min Range: -1.5867

Max Act: 1.0432. Min Act: -0.0000

Data Index: 247601 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.9284. Min Act: -0.0000

Data Index: 347618 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.9065. Min Act: -0.0000

Data Index: 89500 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8699. Min Act: -0.0000

Data Index: 806709 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1346575 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8095. Min Act: -0.0000

Data Index: 542542 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8539. Min Act: -0.0000

Data Index: 387195 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.7931. Min Act: -0.0000

Data Index: 805599 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8410. Min Act: -0.0000

Data Index: 495056 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8268. Min Act: -0.0000

Data Index: 913421 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8273. Min Act: -0.0000

Data Index: 72119 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8086. Min Act: 0.0000

Data Index: 542008 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8147. Min Act: -0.0000

Data Index: 305814 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8035. Min Act: -0.0000

Data Index: 525663 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.8059. Min Act: -0.0000

Data Index: 148048 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 1.5867. Min Range: -1.5867

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1065829 (C4 (Web Text))

Max Activating Token Index: 619