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

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

Neuron 617 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.7403. Min Act: -0.0001

Data Index: 476078 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 4.0111. Min Range: -4.0111

Max Act: 4.0111. Min Act: -0.0001

Data Index: 645564 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.9423. Min Act: -0.0001

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.2584. Min Act: -0.0001

Data Index: 1358194 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.8295. Min Act: -0.0001

Data Index: 775211 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.1047. Min Act: -0.0001

Data Index: 558923 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.8482. Min Act: -0.0001

Data Index: 596845 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.2431. Min Act: -0.0001

Data Index: 337851 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.9577. Min Act: -0.0001

Data Index: 521792 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.9513. Min Act: -0.0001

Data Index: 280249 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.0713. Min Act: -0.0001

Data Index: 150178 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.2172. Min Act: -0.0001

Data Index: 559606 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.1954. Min Act: -0.0001

Data Index: 1175978 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.0502. Min Act: -0.0001

Data Index: 894307 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.9145. Min Act: -0.0001

Data Index: 1210583 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.0634. Min Act: -0.0001

Data Index: 1098014 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.0067. Min Act: -0.0001

Data Index: 505311 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.9667. Min Act: -0.0001

Data Index: 1026199 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 4.0111. Min Range: -4.0111

Max Act: 3.3663. Min Act: -0.0001

Data Index: 1027824 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 4.0111. Min Range: -4.0111

Max Act: 2.9420. Min Act: -0.0001

Data Index: 1167756 (C4 (Web Text))

Max Activating Token Index: 546