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

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

Neuron 1081 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3490. Min Act: -0.0001

Data Index: 842055 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3378. Min Act: -0.0001

Data Index: 895891 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3237. Min Act: -0.0002

Data Index: 481207 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3200. Min Act: -0.0001

Data Index: 505757 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3148. Min Act: -0.0001

Data Index: 709966 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3146. Min Act: -0.0001

Data Index: 1146752 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3152. Min Act: -0.0001

Data Index: 1241632 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3122. Min Act: -0.0001

Data Index: 181611 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1114173 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3021. Min Act: -0.0001

Data Index: 1187710 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2923. Min Act: -0.0001

Data Index: 719481 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2917. Min Act: -0.0001

Data Index: 130570 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2832. Min Act: -0.0002

Data Index: 1362326 (Python Code)

Max Activating Token Index: 256

Text #13

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2895. Min Act: -0.0001

Data Index: 834027 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2891. Min Act: -0.0001

Data Index: 360554 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2817. Min Act: -0.0001

Data Index: 419671 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2718. Min Act: -0.0001

Data Index: 825798 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2811. Min Act: -0.0001

Data Index: 1362599 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2714. Min Act: -0.0001

Data Index: 706383 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2734. Min Act: -0.0001

Data Index: 147355 (C4 (Web Text))

Max Activating Token Index: 866