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

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

Neuron 3210 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0001

Data Index: 34583 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1095. Min Act: -0.0001

Data Index: 669557 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1025. Min Act: -0.0001

Data Index: 928012 (C4 (Web Text))

Max Activating Token Index: 757

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0928. Min Act: -0.0001

Data Index: 684374 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1113078 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0939. Min Act: -0.0001

Data Index: 255660 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0904. Min Act: -0.0001

Data Index: 372381 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0864. Min Act: -0.0001

Data Index: 552281 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0878. Min Act: -0.0001

Data Index: 223370 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0872. Min Act: -0.0001

Data Index: 108442 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1026184 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0850. Min Act: -0.0001

Data Index: 1228253 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0852. Min Act: -0.0001

Data Index: 308600 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0835. Min Act: -0.0000

Data Index: 381543 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0796. Min Act: -0.0001

Data Index: 1129742 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1166811 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0771. Min Act: -0.0001

Data Index: 689921 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0821. Min Act: -0.0001

Data Index: 520025 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0877. Min Act: -0.0001

Data Index: 900714 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0839. Min Act: -0.0001

Data Index: 1014180 (C4 (Web Text))

Max Activating Token Index: 955