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

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

Neuron 3580 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.4037. Min Act: -0.0000

Data Index: 211064 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3001. Min Act: -0.0000

Data Index: 458113 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3307. Min Act: -0.0000

Data Index: 192372 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3304. Min Act: -0.0000

Data Index: 502829 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3022. Min Act: -0.0000

Data Index: 158910 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3028. Min Act: -0.0000

Data Index: 18227 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3042. Min Act: -0.0000

Data Index: 987305 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2776. Min Act: -0.0000

Data Index: 864885 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1319284 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2947. Min Act: -0.0000

Data Index: 98665 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2770. Min Act: -0.0000

Data Index: 574441 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2709. Min Act: -0.0000

Data Index: 99280 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2685. Min Act: -0.0000

Data Index: 591539 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2706. Min Act: -0.0000

Data Index: 290096 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2771. Min Act: -0.0000

Data Index: 480054 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2614. Min Act: -0.0000

Data Index: 598088 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1356891 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2434. Min Act: -0.0000

Data Index: 796988 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2550. Min Act: -0.0000

Data Index: 553040 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2625. Min Act: -0.0000

Data Index: 879856 (C4 (Web Text))

Max Activating Token Index: 543