Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3928 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5827. Min Act: -0.0000

Data Index: 287564 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5361. Min Act: -0.0000

Data Index: 436763 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1344723 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5610. Min Act: -0.0000

Data Index: 820311 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5715. Min Act: -0.0000

Data Index: 308159 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5248. Min Act: -0.0000

Data Index: 982711 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1350312 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5191. Min Act: -0.0000

Data Index: 194165 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5081. Min Act: -0.0000

Data Index: 727557 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1144899 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4616. Min Act: -0.0000

Data Index: 419974 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1158684 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4594. Min Act: -0.0000

Data Index: 154871 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4461. Min Act: -0.0000

Data Index: 1642839 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1014493 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4667. Min Act: -0.0000

Data Index: 674182 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4855. Min Act: -0.0000

Data Index: 655032 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4793. Min Act: -0.0000

Data Index: 742051 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4282. Min Act: -0.0000

Data Index: 784193 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.5827. Min Range: -0.5827

Max Act: 0.4436. Min Act: -0.0000

Data Index: 419477 (C4 (Web Text))

Max Activating Token Index: 947