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

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

Neuron 2862 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.2867. Min Act: -0.0000

Data Index: 740615 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.2203. Min Act: -0.0000

Data Index: 734883 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.1447. Min Act: -0.0000

Data Index: 915019 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1350076 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.1419. Min Act: -0.0000

Data Index: 455863 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.0537. Min Act: -0.0000

Data Index: 965388 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.0425. Min Act: -0.0000

Data Index: 146405 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1300040 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.0456. Min Act: -0.0000

Data Index: 763018 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.0392. Min Act: -0.0000

Data Index: 158334 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 1.2867. Min Range: -1.2867

Max Act: 1.0266. Min Act: -0.0000

Data Index: 527869 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 1.2867. Min Range: -1.2867

Max Act: 0.9660. Min Act: -0.0000

Data Index: 531978 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 1.2867. Min Range: -1.2867

Max Act: 0.9222. Min Act: -0.0000

Data Index: 845899 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 1.2867. Min Range: -1.2867

Max Act: 0.8729. Min Act: -0.0000

Data Index: 871243 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.2867. Min Range: -1.2867

Max Act: 0.9438. Min Act: -0.0000

Data Index: 310882 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 1.2867. Min Range: -1.2867

Max Act: 0.8954. Min Act: -0.0000

Data Index: 73483 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 1.2867. Min Range: -1.2867

Max Act: 0.9499. Min Act: -0.0000

Data Index: 167476 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 1.2867. Min Range: -1.2867

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1054988 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.2867. Min Range: -1.2867

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1198526 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.2867. Min Range: -1.2867

Max Act: 0.8573. Min Act: -0.0000

Data Index: 206092 (C4 (Web Text))

Max Activating Token Index: 805