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

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

Neuron 1968 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.9571. Min Act: -0.0000

Data Index: 483375 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.8906. Min Act: -0.0000

Data Index: 436409 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.6399. Min Act: -0.0000

Data Index: 814989 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.4884. Min Act: -0.0000

Data Index: 63417 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.8388. Min Act: -0.0000

Data Index: 1359446 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.3677. Min Act: -0.0000

Data Index: 696598 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.4738. Min Act: -0.0000

Data Index: 969533 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.6026. Min Act: -0.0000

Data Index: 380 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.6230. Min Act: -0.0000

Data Index: 1149610 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.5927. Min Act: -0.0000

Data Index: 674807 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.8644. Min Act: -0.0000

Data Index: 584760 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.2571. Min Act: -0.0000

Data Index: 839605 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.3115. Min Act: -0.0000

Data Index: 201653 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.1824. Min Act: -0.0000

Data Index: 679575 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.3081. Min Act: -0.0000

Data Index: 1303376 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.1574. Min Act: -0.0000

Data Index: 1074212 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.2580. Min Act: -0.0000

Data Index: 1283051 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 2.9571. Min Range: -2.9571

Max Act: 2.2600. Min Act: -0.0000

Data Index: 353699 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 2.9571. Min Range: -2.9571

Max Act: 1.9151. Min Act: -0.0000

Data Index: 1165576 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 2.9571. Min Range: -2.9571

Max Act: 1.8137. Min Act: -0.0000

Data Index: 846767 (C4 (Web Text))

Max Activating Token Index: 851