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

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

Neuron 2681 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: 0.3248. Min Range: -0.3248

Max Act: 0.3234. Min Act: -0.0000

Data Index: 777789 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.3248. Min Act: -0.0000

Data Index: 813390 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2723. Min Act: -0.0001

Data Index: 570725 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2814. Min Act: -0.0000

Data Index: 349749 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2803. Min Act: -0.0001

Data Index: 123651 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2722. Min Act: -0.0000

Data Index: 455180 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2849. Min Act: -0.0000

Data Index: 264723 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2895. Min Act: -0.0001

Data Index: 869987 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1226660 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2797. Min Act: 0.0000

Data Index: 68090 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2675. Min Act: -0.0000

Data Index: 932447 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2821. Min Act: -0.0001

Data Index: 384599 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2860. Min Act: -0.0001

Data Index: 999597 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2770. Min Act: -0.0001

Data Index: 1344856 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2660. Min Act: -0.0000

Data Index: 982854 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2712. Min Act: -0.0000

Data Index: 787490 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2564. Min Act: -0.0001

Data Index: 407864 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2521. Min Act: -0.0000

Data Index: 3560 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2651. Min Act: -0.0001

Data Index: 796188 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.3248. Min Range: -0.3248

Max Act: 0.2523. Min Act: -0.0000

Data Index: 907410 (C4 (Web Text))

Max Activating Token Index: 83