Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2069 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0747. Min Range: -2.0747

Max Act: 2.0747. Min Act: 0.0002

Data Index: 958227 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 2.0747. Min Range: -2.0747

Max Act: 2.0198. Min Act: 0.0000

Data Index: 1166041 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.7887. Min Act: -0.0000

Data Index: 398393 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.8236. Min Act: 0.0002

Data Index: 840111 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.6128. Min Act: -0.0000

Data Index: 1188064 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.6667. Min Act: -0.0000

Data Index: 30056 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.5655. Min Act: -0.0000

Data Index: 898099 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.5439. Min Act: -0.0000

Data Index: 1304040 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.8104. Min Act: 0.0000

Data Index: 427352 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.6010. Min Act: 0.0001

Data Index: 902284 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.5067. Min Act: 0.0000

Data Index: 614278 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.5804. Min Act: -0.0000

Data Index: 680148 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.5740. Min Act: 0.0000

Data Index: 716652 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.6763. Min Act: 0.0000

Data Index: 304959 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.7578. Min Act: -0.0000

Data Index: 200400 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.4740. Min Act: 0.0001

Data Index: 137137 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.4329. Min Act: 0.0004

Data Index: 1086866 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.4309. Min Act: 0.0001

Data Index: 1199462 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.5287. Min Act: -0.0000

Data Index: 678178 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 2.0747. Min Range: -2.0747

Max Act: 1.4783. Min Act: -0.0000

Data Index: 531436 (C4 (Web Text))

Max Activating Token Index: 112