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

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

Neuron 2513 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1229962 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0793. Min Act: -0.0001

Data Index: 264141 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0735. Min Act: -0.0001

Data Index: 575671 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0709. Min Act: -0.0002

Data Index: 513672 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0704. Min Act: -0.0001

Data Index: 869247 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0680. Min Act: -0.0001

Data Index: 775507 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1286604 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1077018 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0743. Min Act: -0.0002

Data Index: 532975 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0689. Min Act: -0.0001

Data Index: 326295 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1265262 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0709. Min Act: -0.0002

Data Index: 574961 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0677. Min Act: -0.0002

Data Index: 72182 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0723. Min Act: -0.0002

Data Index: 302383 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1018902 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0660. Min Act: -0.0002

Data Index: 605558 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0614. Min Act: -0.0002

Data Index: 578289 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1306749 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1248622 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0586. Min Act: -0.0002

Data Index: 351135 (C4 (Web Text))

Max Activating Token Index: 716