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

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

Neuron 1690 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.9071. Min Act: -0.0001

Data Index: 1158878 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.9470. Min Act: -0.0001

Data Index: 254144 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.8526. Min Act: -0.0001

Data Index: 1335830 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.8977. Min Act: -0.0001

Data Index: 187911 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.6975. Min Act: -0.0001

Data Index: 955578 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.9296. Min Act: -0.0001

Data Index: 478012 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.7646. Min Act: -0.0001

Data Index: 1273108 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.7014. Min Act: -0.0001

Data Index: 494051 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.5938. Min Act: -0.0001

Data Index: 984200 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.7290. Min Act: -0.0001

Data Index: 1048665 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.7659. Min Act: -0.0001

Data Index: 74407 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.7011. Min Act: -0.0001

Data Index: 821783 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.7718. Min Act: -0.0001

Data Index: 415472 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.6705. Min Act: -0.0001

Data Index: 575426 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.5195. Min Act: -0.0001

Data Index: 1112970 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.5982. Min Act: -0.0001

Data Index: 312814 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.5524. Min Act: -0.0001

Data Index: 144561 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.5893. Min Act: -0.0001

Data Index: 363505 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.5760. Min Act: -0.0001

Data Index: 751876 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.9470. Min Range: -1.9470

Max Act: 1.5387. Min Act: -0.0001

Data Index: 872886 (C4 (Web Text))

Max Activating Token Index: 77