Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3827 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3820. Min Act: -0.0003

Data Index: 1212098 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3750. Min Act: -0.0002

Data Index: 103843 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3416. Min Act: -0.0002

Data Index: 813309 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3344. Min Act: -0.0002

Data Index: 1542396 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3175. Min Act: -0.0003

Data Index: 1271840 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3138. Min Act: -0.0002

Data Index: 1587091 (Python Code)

Max Activating Token Index: 553

Text #6

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3079. Min Act: -0.0003

Data Index: 884048 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3055. Min Act: -0.0002

Data Index: 616463 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.3138. Min Act: -0.0002

Data Index: 1514585 (Python Code)

Max Activating Token Index: 687

Text #9

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2934. Min Act: -0.0003

Data Index: 462737 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2706. Min Act: -0.0003

Data Index: 1259354 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2894. Min Act: -0.0003

Data Index: 1151064 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2886. Min Act: -0.0003

Data Index: 525041 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2862. Min Act: -0.0003

Data Index: 761973 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2827. Min Act: -0.0003

Data Index: 601255 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2809. Min Act: -0.0002

Data Index: 773605 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2793. Min Act: -0.0003

Data Index: 402299 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2773. Min Act: -0.0002

Data Index: 660887 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2770. Min Act: -0.0003

Data Index: 1297645 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.3820. Min Range: -0.3820

Max Act: 0.2757. Min Act: -0.0003

Data Index: 25683 (C4 (Web Text))

Max Activating Token Index: 237