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

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

Neuron 3775 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: 0.8688. Min Range: -0.8688

Max Act: 0.8688. Min Act: -0.0000

Data Index: 297522 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1062098 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1332565 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7039. Min Act: -0.0000

Data Index: 964740 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1024340 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1024027 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1337505 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6137. Min Act: -0.0000

Data Index: 694598 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6215. Min Act: 0.0000

Data Index: 179463 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6908. Min Act: -0.0000

Data Index: 51463 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6467. Min Act: 0.0000

Data Index: 862995 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6255. Min Act: -0.0000

Data Index: 284693 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1281704 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6175. Min Act: -0.0000

Data Index: 30455 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1238923 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6478. Min Act: -0.0000

Data Index: 693976 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1185738 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6393. Min Act: -0.0000

Data Index: 144057 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6001. Min Act: -0.0000

Data Index: 662182 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6204. Min Act: -0.0000

Data Index: 264458 (C4 (Web Text))

Max Activating Token Index: 385