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

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

Neuron 3733 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: 0.9527. Min Range: -0.9527

Max Act: 0.9527. Min Act: -0.0001

Data Index: 339231 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7037. Min Act: -0.0001

Data Index: 833283 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6966. Min Act: -0.0001

Data Index: 1043935 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6942. Min Act: -0.0001

Data Index: 606806 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6375. Min Act: -0.0001

Data Index: 266149 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7770. Min Act: -0.0001

Data Index: 1018937 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7606. Min Act: -0.0001

Data Index: 600153 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7236. Min Act: -0.0001

Data Index: 243326 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6821. Min Act: -0.0001

Data Index: 1010591 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6615. Min Act: -0.0001

Data Index: 882791 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6409. Min Act: -0.0001

Data Index: 817190 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6828. Min Act: -0.0001

Data Index: 1077223 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6150. Min Act: -0.0001

Data Index: 1209927 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6817. Min Act: -0.0001

Data Index: 543146 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6335. Min Act: -0.0001

Data Index: 657818 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.5912. Min Act: -0.0001

Data Index: 222884 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6707. Min Act: -0.0001

Data Index: 305355 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.5813. Min Act: -0.0001

Data Index: 319952 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6013. Min Act: -0.0001

Data Index: 61295 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6265. Min Act: -0.0001

Data Index: 1197193 (C4 (Web Text))

Max Activating Token Index: 499