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

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

Neuron 2984 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.1153. Min Act: -0.0003

Data Index: 782841 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9009. Min Act: -0.0003

Data Index: 379460 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8872. Min Act: -0.0003

Data Index: 204047 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8942. Min Act: -0.0003

Data Index: 829511 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8916. Min Act: -0.0003

Data Index: 477219 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8738. Min Act: -0.0003

Data Index: 635820 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8374. Min Act: -0.0003

Data Index: 524390 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.7812. Min Act: -0.0003

Data Index: 496483 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8783. Min Act: -0.0003

Data Index: 1182735 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8619. Min Act: -0.0003

Data Index: 452296 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.7997. Min Act: -0.0003

Data Index: 293292 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9100. Min Act: -0.0003

Data Index: 791875 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8112. Min Act: -0.0003

Data Index: 651527 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.7912. Min Act: -0.0003

Data Index: 1194853 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.7846. Min Act: -0.0003

Data Index: 908326 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.7557. Min Act: -0.0003

Data Index: 799981 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8279. Min Act: -0.0003

Data Index: 58611 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.7318. Min Act: -0.0003

Data Index: 1095207 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8729. Min Act: -0.0003

Data Index: 1128459 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.7489. Min Act: -0.0003

Data Index: 997687 (C4 (Web Text))

Max Activating Token Index: 632