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

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

Neuron 312 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0972. Min Act: -0.0001

Data Index: 415198 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0997. Min Act: -0.0001

Data Index: 990996 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0939. Min Act: -0.0002

Data Index: 804343 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0866. Min Act: -0.0002

Data Index: 310792 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0894. Min Act: -0.0002

Data Index: 383485 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0944. Min Act: -0.0001

Data Index: 777373 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1352125 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0903. Min Act: -0.0002

Data Index: 828813 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0897. Min Act: -0.0001

Data Index: 281632 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1539601 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0827. Min Act: -0.0001

Data Index: 968917 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0925. Min Act: -0.0001

Data Index: 375520 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0889. Min Act: -0.0001

Data Index: 711821 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0788. Min Act: -0.0001

Data Index: 192596 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1197131 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0878. Min Act: -0.0001

Data Index: 181325 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0870. Min Act: -0.0001

Data Index: 766810 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0949. Min Act: -0.0002

Data Index: 561064 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0870. Min Act: -0.0001

Data Index: 625674 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0831. Min Act: -0.0001

Data Index: 991918 (C4 (Web Text))

Max Activating Token Index: 307