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

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

Neuron 2953 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.2834. Min Act: -0.0001

Data Index: 990600 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0789. Min Act: -0.0001

Data Index: 705925 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.2834. Min Range: -1.2834

Max Act: 1.0458. Min Act: -0.0001

Data Index: 943640 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.9370. Min Act: -0.0001

Data Index: 1206133 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.9130. Min Act: -0.0001

Data Index: 291739 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.9857. Min Act: -0.0001

Data Index: 1348355 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.9494. Min Act: -0.0001

Data Index: 547410 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.8817. Min Act: -0.0001

Data Index: 920379 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.9498. Min Act: -0.0001

Data Index: 883161 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.7730. Min Act: -0.0001

Data Index: 1170689 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.8670. Min Act: -0.0001

Data Index: 680585 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.8568. Min Act: -0.0001

Data Index: 1304813 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.8540. Min Act: -0.0001

Data Index: 85499 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.8601. Min Act: -0.0001

Data Index: 238732 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.8182. Min Act: -0.0001

Data Index: 118028 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.8007. Min Act: -0.0001

Data Index: 1254924 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.7916. Min Act: -0.0001

Data Index: 1161751 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.7506. Min Act: -0.0001

Data Index: 251783 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.8020. Min Act: -0.0001

Data Index: 493775 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 1.2834. Min Range: -1.2834

Max Act: 0.8016. Min Act: -0.0001

Data Index: 695829 (C4 (Web Text))

Max Activating Token Index: 899