Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 750 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5885. Min Act: -0.0001

Data Index: 455605 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5556. Min Act: -0.0001

Data Index: 1039003 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5746. Min Act: -0.0001

Data Index: 165326 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4962. Min Act: -0.0001

Data Index: 367806 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5708. Min Act: -0.0001

Data Index: 584853 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5206. Min Act: -0.0001

Data Index: 633524 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4173. Min Act: -0.0001

Data Index: 1272125 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5056. Min Act: -0.0001

Data Index: 778197 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4799. Min Act: -0.0001

Data Index: 258442 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4772. Min Act: -0.0001

Data Index: 1248766 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5027. Min Act: -0.0001

Data Index: 2692 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4246. Min Act: -0.0001

Data Index: 1118886 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5007. Min Act: -0.0001

Data Index: 1357606 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4842. Min Act: -0.0001

Data Index: 497186 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4749. Min Act: -0.0001

Data Index: 1153987 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1019614 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4590. Min Act: -0.0001

Data Index: 553889 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4427. Min Act: -0.0001

Data Index: 840952 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4711. Min Act: -0.0001

Data Index: 1237407 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5162. Min Act: -0.0001

Data Index: 808899 (C4 (Web Text))

Max Activating Token Index: 885