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

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

Neuron 1595 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.3679. Min Act: -0.0001

Data Index: 1322257 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.3596. Min Act: -0.0000

Data Index: 518697 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.3490. Min Act: -0.0001

Data Index: 439218 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2996. Min Act: -0.0001

Data Index: 162113 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2831. Min Act: -0.0001

Data Index: 866434 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2866. Min Act: -0.0001

Data Index: 586031 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1103094 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2745. Min Act: -0.0000

Data Index: 505845 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2700. Min Act: -0.0001

Data Index: 833574 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2638. Min Act: -0.0000

Data Index: 915420 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1050830 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2582. Min Act: -0.0001

Data Index: 964449 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2300. Min Act: -0.0000

Data Index: 366425 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2529. Min Act: -0.0001

Data Index: 728336 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2449. Min Act: -0.0001

Data Index: 572979 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2619. Min Act: -0.0001

Data Index: 861440 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2471. Min Act: -0.0001

Data Index: 219481 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2476. Min Act: -0.0001

Data Index: 822615 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2624. Min Act: -0.0001

Data Index: 523642 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.3679. Min Range: -0.3679

Max Act: 0.2425. Min Act: -0.0001

Data Index: 409087 (C4 (Web Text))

Max Activating Token Index: 917