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

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

Neuron 4768 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7791. Min Act: -0.0001

Data Index: 220226 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.8458. Min Act: -0.0000

Data Index: 486494 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1352453 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7597. Min Act: -0.0001

Data Index: 1188899 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7203. Min Act: -0.0000

Data Index: 302957 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7756. Min Act: -0.0000

Data Index: 428458 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7603. Min Act: -0.0001

Data Index: 415010 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7126. Min Act: -0.0000

Data Index: 587767 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6924. Min Act: -0.0000

Data Index: 362587 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6894. Min Act: -0.0001

Data Index: 971436 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6911. Min Act: -0.0000

Data Index: 146220 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7096. Min Act: -0.0001

Data Index: 577203 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6895. Min Act: -0.0000

Data Index: 184629 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6855. Min Act: -0.0001

Data Index: 639052 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1119462 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7243. Min Act: -0.0001

Data Index: 920223 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.7183. Min Act: -0.0001

Data Index: 1100415 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6946. Min Act: -0.0000

Data Index: 365097 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6659. Min Act: -0.0001

Data Index: 255907 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.8458. Min Range: -0.8458

Max Act: 0.6825. Min Act: -0.0000

Data Index: 905778 (C4 (Web Text))

Max Activating Token Index: 991