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

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

Neuron 2867 in Layer 1

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: 0.1020. Min Range: -0.1020

Max Act: 0.1020. Min Act: -0.0002

Data Index: 717099 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1075513 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0978. Min Act: -0.0002

Data Index: 954331 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0938. Min Act: -0.0002

Data Index: 230917 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1007657 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0972. Min Act: -0.0002

Data Index: 300692 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0933. Min Act: -0.0002

Data Index: 947267 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0917. Min Act: -0.0003

Data Index: 1203180 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0923. Min Act: -0.0002

Data Index: 439906 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0938. Min Act: -0.0002

Data Index: 323843 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0896. Min Act: -0.0002

Data Index: 758295 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0907. Min Act: -0.0002

Data Index: 982607 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0901. Min Act: -0.0002

Data Index: 638175 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1082317 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0887. Min Act: -0.0002

Data Index: 948706 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0910. Min Act: -0.0002

Data Index: 975371 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0886. Min Act: -0.0002

Data Index: 734663 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0883. Min Act: -0.0002

Data Index: 60027 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0884. Min Act: -0.0002

Data Index: 493754 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0894. Min Act: -0.0002

Data Index: 488382 (C4 (Web Text))

Max Activating Token Index: 773