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

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

Neuron 2009 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0891. Min Act: -0.0002

Data Index: 878415 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0661. Min Act: -0.0002

Data Index: 136358 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0656. Min Act: -0.0002

Data Index: 723549 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0560. Min Act: -0.0002

Data Index: 302628 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0552. Min Act: -0.0002

Data Index: 267439 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0522. Min Act: -0.0002

Data Index: 662825 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0520. Min Act: -0.0002

Data Index: 67576 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0471. Min Act: -0.0002

Data Index: 837004 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0449. Min Act: -0.0002

Data Index: 9420 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0458. Min Act: -0.0002

Data Index: 345123 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1215014 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0451. Min Act: -0.0002

Data Index: 581663 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0436. Min Act: -0.0002

Data Index: 197231 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0436. Min Act: -0.0002

Data Index: 989029 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1119631 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0429. Min Act: -0.0002

Data Index: 475793 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0436. Min Act: -0.0002

Data Index: 835033 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0413. Min Act: -0.0002

Data Index: 422519 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0424. Min Act: -0.0002

Data Index: 36303 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.0891. Min Range: -0.0891

Max Act: 0.0404. Min Act: -0.0002

Data Index: 948461 (C4 (Web Text))

Max Activating Token Index: 198