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

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

Neuron 641 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: 0.1053. Min Range: -0.1053

Max Act: 0.1053. Min Act: -0.0001

Data Index: 744265 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1049. Min Act: -0.0001

Data Index: 668865 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0970. Min Act: -0.0001

Data Index: 433110 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1163803 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1029. Min Act: -0.0001

Data Index: 122831 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0861. Min Act: -0.0001

Data Index: 126460 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0890. Min Act: -0.0001

Data Index: 276266 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0756. Min Act: -0.0001

Data Index: 326137 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0885. Min Act: -0.0001

Data Index: 167415 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0849. Min Act: -0.0001

Data Index: 409326 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1228218 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0800. Min Act: -0.0001

Data Index: 1273953 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1070464 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0823. Min Act: -0.0001

Data Index: 231800 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0731. Min Act: -0.0001

Data Index: 282540 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0805. Min Act: -0.0001

Data Index: 249711 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0775. Min Act: -0.0001

Data Index: 197889 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0821. Min Act: -0.0001

Data Index: 16539 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0820. Min Act: -0.0001

Data Index: 360921 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0803. Min Act: -0.0001

Data Index: 251150 (C4 (Web Text))

Max Activating Token Index: 10