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

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

Neuron 1910 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.5927. Min Act: -0.0001

Data Index: 1024469 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.5503. Min Act: -0.0001

Data Index: 431080 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.5149. Min Act: -0.0001

Data Index: 1307944 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.5275. Min Act: -0.0001

Data Index: 885974 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4853. Min Act: -0.0000

Data Index: 910684 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.5021. Min Act: -0.0001

Data Index: 1076535 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4959. Min Act: -0.0001

Data Index: 510640 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4782. Min Act: -0.0001

Data Index: 665274 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4895. Min Act: -0.0001

Data Index: 137462 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1023229 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4942. Min Act: -0.0001

Data Index: 1059045 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4776. Min Act: -0.0001

Data Index: 430809 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.5441. Min Act: -0.0001

Data Index: 838016 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.5048. Min Act: -0.0001

Data Index: 235098 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4591. Min Act: -0.0001

Data Index: 1016960 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4098. Min Act: -0.0001

Data Index: 403927 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.5018. Min Act: -0.0000

Data Index: 977249 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1342800 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4606. Min Act: -0.0001

Data Index: 446760 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.5927. Min Range: -0.5927

Max Act: 0.4763. Min Act: -0.0000

Data Index: 898919 (C4 (Web Text))

Max Activating Token Index: 427