Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2618 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1017198 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.4265. Min Act: -0.0000

Data Index: 145722 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.4308. Min Act: -0.0000

Data Index: 383548 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3708. Min Act: -0.0000

Data Index: 845549 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3028. Min Act: -0.0000

Data Index: 877264 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3069. Min Act: -0.0000

Data Index: 681205 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.3133. Min Act: -0.0000

Data Index: 114392 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2835. Min Act: -0.0000

Data Index: 626604 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2959. Min Act: -0.0000

Data Index: 748614 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1027977 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2745. Min Act: -0.0000

Data Index: 254722 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2647. Min Act: -0.0000

Data Index: 852282 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1632701 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1020958 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2392. Min Act: -0.0000

Data Index: 453338 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1563507 (Python Code)

Max Activating Token Index: 855

Text #16

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1632291 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2225. Min Act: -0.0000

Data Index: 999943 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2502. Min Act: -0.0000

Data Index: 927316 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.4308. Min Range: -0.4308

Max Act: 0.2097. Min Act: -0.0000

Data Index: 259191 (C4 (Web Text))

Max Activating Token Index: 818