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

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

Neuron 1392 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3146. Min Range: -2.3146

Max Act: 2.3146. Min Act: -0.0001

Data Index: 176521 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 2.3146. Min Range: -2.3146

Max Act: 2.3068. Min Act: -0.0000

Data Index: 724798 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 2.3146. Min Range: -2.3146

Max Act: 2.1628. Min Act: -0.0001

Data Index: 1313759 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 2.3146. Min Range: -2.3146

Max Act: 2.2149. Min Act: -0.0000

Data Index: 176485 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.9908. Min Act: -0.0001

Data Index: 13512 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.9451. Min Act: -0.0001

Data Index: 1068771 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 2.3146. Min Range: -2.3146

Max Act: 2.2565. Min Act: -0.0001

Data Index: 494754 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.8207. Min Act: -0.0000

Data Index: 399893 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.8931. Min Act: -0.0001

Data Index: 1201459 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.7574. Min Act: -0.0000

Data Index: 941894 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.8509. Min Act: -0.0000

Data Index: 1172641 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.9443. Min Act: -0.0000

Data Index: 1019952 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.8486. Min Act: -0.0001

Data Index: 1043421 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.7105. Min Act: -0.0000

Data Index: 80293 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.8946. Min Act: -0.0000

Data Index: 1174278 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.7827. Min Act: -0.0001

Data Index: 316560 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.7832. Min Act: -0.0000

Data Index: 541905 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.6739. Min Act: -0.0001

Data Index: 802839 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.6785. Min Act: -0.0000

Data Index: 156979 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 2.3146. Min Range: -2.3146

Max Act: 1.7342. Min Act: -0.0000

Data Index: 986661 (C4 (Web Text))

Max Activating Token Index: 44