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

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

Neuron 2738 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.9644. Min Act: -0.0000

Data Index: 846900 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1335087 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8832. Min Act: -0.0000

Data Index: 217015 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8592. Min Act: -0.0000

Data Index: 492057 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7950. Min Act: -0.0000

Data Index: 34899 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8223. Min Act: -0.0000

Data Index: 824932 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1352875 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7661. Min Act: -0.0000

Data Index: 112948 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.7747. Min Act: -0.0000

Data Index: 872998 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1198073 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6917. Min Act: -0.0000

Data Index: 269745 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1139821 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1217040 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6164. Min Act: -0.0000

Data Index: 660404 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6498. Min Act: -0.0000

Data Index: 174167 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6298. Min Act: -0.0000

Data Index: 544510 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6273. Min Act: -0.0000

Data Index: 42313 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6213. Min Act: -0.0000

Data Index: 525401 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6253. Min Act: -0.0000

Data Index: 266431 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.9644. Min Range: -0.9644

Max Act: 0.6257. Min Act: -0.0000

Data Index: 958624 (C4 (Web Text))

Max Activating Token Index: 618