Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3794 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8103. Min Act: -0.0001

Data Index: 941697 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8581. Min Act: -0.0001

Data Index: 218632 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8023. Min Act: -0.0002

Data Index: 47865 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7866. Min Act: -0.0002

Data Index: 1151666 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7891. Min Act: -0.0001

Data Index: 109640 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7610. Min Act: -0.0002

Data Index: 909838 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7158. Min Act: -0.0001

Data Index: 8564 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7284. Min Act: -0.0001

Data Index: 1046978 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.8065. Min Act: -0.0001

Data Index: 166384 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7445. Min Act: -0.0002

Data Index: 1155633 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7912. Min Act: -0.0001

Data Index: 268822 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7821. Min Act: -0.0002

Data Index: 402991 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7853. Min Act: -0.0002

Data Index: 1232777 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7846. Min Act: -0.0002

Data Index: 393397 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7606. Min Act: -0.0002

Data Index: 1339543 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7512. Min Act: -0.0001

Data Index: 1119288 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7739. Min Act: -0.0001

Data Index: 599740 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7738. Min Act: -0.0002

Data Index: 319444 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.7057. Min Act: -0.0002

Data Index: 866180 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.8581. Min Range: -0.8581

Max Act: 0.6984. Min Act: -0.0002

Data Index: 321580 (C4 (Web Text))

Max Activating Token Index: 67