Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6118 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1129330 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1149258 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1261718 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0001

Data Index: 821716 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0739. Min Act: -0.0001

Data Index: 887479 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1185028 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0696. Min Act: -0.0001

Data Index: 124458 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0722. Min Act: -0.0001

Data Index: 899624 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0713. Min Act: -0.0001

Data Index: 350681 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0658. Min Act: -0.0001

Data Index: 538192 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0701. Min Act: -0.0001

Data Index: 488918 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1339587 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0679. Min Act: -0.0001

Data Index: 867960 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0697. Min Act: -0.0001

Data Index: 818847 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1244756 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0594. Min Act: -0.0001

Data Index: 383985 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0684. Min Act: -0.0001

Data Index: 692187 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0611. Min Act: -0.0001

Data Index: 71448 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1078941 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0530. Min Act: -0.0001

Data Index: 778926 (C4 (Web Text))

Max Activating Token Index: 793