Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2408 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1739. Min Range: -1.1739

Max Act: 1.1739. Min Act: -0.0001

Data Index: 764621 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.9013. Min Act: -0.0001

Data Index: 14490 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.9025. Min Act: -0.0001

Data Index: 1328308 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.8202. Min Act: -0.0001

Data Index: 661824 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.8377. Min Act: -0.0001

Data Index: 408915 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7847. Min Act: -0.0001

Data Index: 709704 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.8103. Min Act: -0.0001

Data Index: 1098178 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7861. Min Act: -0.0001

Data Index: 455383 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7758. Min Act: -0.0001

Data Index: 971094 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.8302. Min Act: -0.0001

Data Index: 576881 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7975. Min Act: -0.0001

Data Index: 1125400 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7700. Min Act: -0.0001

Data Index: 119947 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7373. Min Act: -0.0001

Data Index: 866944 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7765. Min Act: -0.0001

Data Index: 663009 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7698. Min Act: -0.0001

Data Index: 1124829 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7699. Min Act: -0.0001

Data Index: 1214171 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7738. Min Act: -0.0001

Data Index: 397906 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7408. Min Act: -0.0001

Data Index: 1001546 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.8070. Min Act: -0.0001

Data Index: 668863 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.1739. Min Range: -1.1739

Max Act: 0.7639. Min Act: -0.0001

Data Index: 100229 (C4 (Web Text))

Max Activating Token Index: 109