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

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

Neuron 458 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: 4.2416. Min Range: -4.2416

Max Act: 4.2416. Min Act: -0.0000

Data Index: 380426 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 4.2416. Min Range: -4.2416

Max Act: 4.1856. Min Act: -0.0000

Data Index: 1078486 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 4.2416. Min Range: -4.2416

Max Act: 4.1001. Min Act: -0.0000

Data Index: 1112016 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.6997. Min Act: -0.0000

Data Index: 373821 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.5507. Min Act: -0.0000

Data Index: 215336 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.4596. Min Act: -0.0000

Data Index: 949952 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.3499. Min Act: -0.0000

Data Index: 871406 (C4 (Web Text))

Max Activating Token Index: 797

Text #7

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.8334. Min Act: -0.0000

Data Index: 994620 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.5024. Min Act: -0.0000

Data Index: 419031 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.4596. Min Act: -0.0000

Data Index: 1100156 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.6123. Min Act: -0.0000

Data Index: 1235980 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 4.2416. Min Range: -4.2416

Max Act: 4.2035. Min Act: -0.0000

Data Index: 114659 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.4692. Min Act: -0.0000

Data Index: 1180957 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.4582. Min Act: -0.0000

Data Index: 584884 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.2755. Min Act: -0.0000

Data Index: 250175 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.4849. Min Act: -0.0000

Data Index: 805114 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.7887. Min Act: -0.0000

Data Index: 1015452 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.4682. Min Act: -0.0000

Data Index: 294161 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.1431. Min Act: -0.0000

Data Index: 43394 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 4.2416. Min Range: -4.2416

Max Act: 3.4275. Min Act: -0.0000

Data Index: 1321654 (C4 (Web Text))

Max Activating Token Index: 574