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

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

Neuron 1860 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1180673 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.4915. Min Act: -0.0000

Data Index: 857508 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1064968 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.3028. Min Act: -0.0000

Data Index: 13265 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.3003. Min Act: -0.0000

Data Index: 554542 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.3350. Min Act: -0.0000

Data Index: 748572 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2949. Min Act: -0.0000

Data Index: 986364 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1277685 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1340899 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2902. Min Act: -0.0000

Data Index: 765611 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2625. Min Act: -0.0000

Data Index: 143149 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2591. Min Act: -0.0000

Data Index: 871621 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1110924 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2759. Min Act: -0.0000

Data Index: 250231 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2592. Min Act: -0.0000

Data Index: 792797 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1175028 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1091923 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1069649 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.1818. Min Act: -0.0000

Data Index: 11280 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.5373. Min Range: -0.5373

Max Act: 0.2738. Min Act: -0.0000

Data Index: 424150 (C4 (Web Text))

Max Activating Token Index: 389