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

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

Neuron 3623 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2945. Min Act: -0.0000

Data Index: 785977 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1262704 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2909. Min Act: -0.0000

Data Index: 221225 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2888. Min Act: -0.0000

Data Index: 716635 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2966. Min Act: -0.0000

Data Index: 125740 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1004061 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1139198 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1216574 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2526. Min Act: -0.0000

Data Index: 564961 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2679. Min Act: -0.0000

Data Index: 568032 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1183688 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2483. Min Act: -0.0000

Data Index: 169983 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2464. Min Act: -0.0000

Data Index: 272050 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2526. Min Act: -0.0000

Data Index: 795699 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2488. Min Act: -0.0000

Data Index: 624689 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2453. Min Act: -0.0000

Data Index: 385708 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2606. Min Act: -0.0000

Data Index: 646598 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2680. Min Act: -0.0000

Data Index: 747890 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2337. Min Act: -0.0000

Data Index: 839996 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.2966. Min Range: -0.2966

Max Act: 0.2636. Min Act: -0.0000

Data Index: 934218 (C4 (Web Text))

Max Activating Token Index: 710