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

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

Neuron 3270 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1003. Min Act: -0.0002

Data Index: 442031 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1226062 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1345022 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0958. Min Act: -0.0002

Data Index: 651591 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0991. Min Act: -0.0002

Data Index: 262538 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0983. Min Act: -0.0002

Data Index: 843098 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0897. Min Act: -0.0002

Data Index: 837220 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1065647 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0954. Min Act: -0.0002

Data Index: 173085 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0922. Min Act: -0.0002

Data Index: 40650 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0908. Min Act: -0.0002

Data Index: 814472 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0936. Min Act: -0.0002

Data Index: 569428 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0883. Min Act: -0.0002

Data Index: 827576 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0832. Min Act: -0.0002

Data Index: 879212 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0812. Min Act: -0.0002

Data Index: 656778 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0866. Min Act: -0.0002

Data Index: 888639 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1376846 (Python Code)

Max Activating Token Index: 466

Text #17

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0821. Min Act: -0.0002

Data Index: 396155 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0921. Min Act: -0.0002

Data Index: 452945 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.1042. Min Range: -0.1042

Max Act: 0.0938. Min Act: -0.0002

Data Index: 24421 (C4 (Web Text))

Max Activating Token Index: 220