Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3383 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.9670. Min Act: -0.0001

Data Index: 698036 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1235340 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7168. Min Act: -0.0001

Data Index: 879114 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6770. Min Act: -0.0001

Data Index: 733333 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6981. Min Act: -0.0001

Data Index: 1059275 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.7403. Min Act: -0.0000

Data Index: 599784 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5284. Min Act: -0.0001

Data Index: 447444 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.6425. Min Act: -0.0001

Data Index: 594271 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5768. Min Act: -0.0001

Data Index: 360626 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5342. Min Act: -0.0000

Data Index: 234497 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.4805. Min Act: -0.0001

Data Index: 252622 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.4747. Min Act: -0.0001

Data Index: 555027 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.4719. Min Act: -0.0000

Data Index: 724371 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.5037. Min Act: -0.0000

Data Index: 618759 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1288525 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.4767. Min Act: -0.0000

Data Index: 244675 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.4699. Min Act: -0.0001

Data Index: 128798 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.4710. Min Act: -0.0000

Data Index: 689246 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.4706. Min Act: -0.0001

Data Index: 1045376 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.9670. Min Range: -0.9670

Max Act: 0.4608. Min Act: -0.0001

Data Index: 627316 (C4 (Web Text))

Max Activating Token Index: 176