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

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

Neuron 3502 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4917. Min Act: -0.0003

Data Index: 905682 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3402. Min Act: -0.0003

Data Index: 413809 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3277. Min Act: -0.0003

Data Index: 53081 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2878. Min Act: -0.0003

Data Index: 818317 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2822. Min Act: -0.0003

Data Index: 833305 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2799. Min Act: -0.0003

Data Index: 538206 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2692. Min Act: -0.0003

Data Index: 1216589 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2650. Min Act: -0.0003

Data Index: 893395 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2701. Min Act: -0.0003

Data Index: 378161 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2603. Min Act: -0.0003

Data Index: 904742 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2691. Min Act: -0.0003

Data Index: 241869 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2662. Min Act: -0.0003

Data Index: 625200 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2564. Min Act: -0.0003

Data Index: 190913 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2649. Min Act: -0.0003

Data Index: 985559 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2647. Min Act: -0.0003

Data Index: 560938 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2642. Min Act: -0.0003

Data Index: 1090014 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2635. Min Act: -0.0003

Data Index: 163839 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2710. Min Act: -0.0003

Data Index: 717878 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2616. Min Act: -0.0003

Data Index: 631885 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.2605. Min Act: -0.0003

Data Index: 396795 (C4 (Web Text))

Max Activating Token Index: 505