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

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

Neuron 3754 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.7061. Min Act: -0.0000

Data Index: 424649 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.5502. Min Act: -0.0000

Data Index: 581753 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.4967. Min Act: -0.0000

Data Index: 499316 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.4155. Min Act: -0.0000

Data Index: 91231 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.4523. Min Act: -0.0000

Data Index: 627343 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1025136 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.4400. Min Act: -0.0000

Data Index: 356083 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1016516 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.4200. Min Act: -0.0000

Data Index: 214518 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3847. Min Act: -0.0000

Data Index: 205966 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3605. Min Act: -0.0000

Data Index: 351591 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1104886 (C4 (Web Text))

Max Activating Token Index: 501

Text #12

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3806. Min Act: -0.0000

Data Index: 132675 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3669. Min Act: -0.0000

Data Index: 29910 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3714. Min Act: -0.0000

Data Index: 971371 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1060262 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3355. Min Act: -0.0000

Data Index: 562265 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3439. Min Act: -0.0000

Data Index: 945865 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3181. Min Act: -0.0000

Data Index: 62652 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.7061. Min Range: -0.7061

Max Act: 0.3488. Min Act: -0.0000

Data Index: 214391 (C4 (Web Text))

Max Activating Token Index: 271