Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2972 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1024132 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1221114 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0853. Min Act: -0.0001

Data Index: 206778 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0853. Min Act: -0.0001

Data Index: 425237 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0896. Min Act: -0.0001

Data Index: 401463 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0831. Min Act: -0.0001

Data Index: 906011 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1272600 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0739. Min Act: -0.0001

Data Index: 862164 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0737. Min Act: -0.0001

Data Index: 972130 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0740. Min Act: -0.0001

Data Index: 302476 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0708. Min Act: -0.0001

Data Index: 969976 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0670. Min Act: -0.0001

Data Index: 706302 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0722. Min Act: -0.0001

Data Index: 430084 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0761. Min Act: -0.0001

Data Index: 873675 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0699. Min Act: -0.0001

Data Index: 589056 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0743. Min Act: -0.0001

Data Index: 198770 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1148068 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1139897 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1149118 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1084165 (C4 (Web Text))

Max Activating Token Index: 78