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

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

Neuron 5006 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.9688. Min Act: -0.0001

Data Index: 866505 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.8502. Min Act: -0.0001

Data Index: 938371 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.8672. Min Act: -0.0001

Data Index: 1274771 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6473. Min Act: -0.0001

Data Index: 935992 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7746. Min Act: -0.0001

Data Index: 1114554 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7637. Min Act: -0.0001

Data Index: 235625 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7121. Min Act: -0.0001

Data Index: 583972 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6732. Min Act: -0.0001

Data Index: 410810 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7327. Min Act: -0.0001

Data Index: 1240914 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6880. Min Act: -0.0001

Data Index: 317429 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6940. Min Act: -0.0001

Data Index: 439949 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7171. Min Act: -0.0001

Data Index: 1071132 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1327536 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1171567 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6726. Min Act: -0.0001

Data Index: 940872 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6414. Min Act: -0.0001

Data Index: 94213 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7559. Min Act: -0.0001

Data Index: 1068895 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.7033. Min Act: -0.0001

Data Index: 604380 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6605. Min Act: -0.0001

Data Index: 918503 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.9688. Min Range: -0.9688

Max Act: 0.6602. Min Act: -0.0001

Data Index: 665983 (C4 (Web Text))

Max Activating Token Index: 750