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

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

Neuron 1468 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.9035. Min Act: -0.0001

Data Index: 484352 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.8671. Min Act: -0.0001

Data Index: 335242 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6622. Min Act: -0.0001

Data Index: 171758 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6624. Min Act: -0.0001

Data Index: 415877 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6451. Min Act: -0.0001

Data Index: 880707 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6822. Min Act: -0.0001

Data Index: 518174 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5847. Min Act: -0.0001

Data Index: 39385 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5562. Min Act: -0.0001

Data Index: 1286222 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5792. Min Act: -0.0001

Data Index: 350156 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5892. Min Act: -0.0001

Data Index: 82463 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5923. Min Act: -0.0001

Data Index: 427349 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5849. Min Act: -0.0001

Data Index: 736448 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5799. Min Act: -0.0001

Data Index: 683057 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5811. Min Act: -0.0001

Data Index: 753801 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5551. Min Act: -0.0001

Data Index: 1150120 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5528. Min Act: -0.0001

Data Index: 1007314 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5704. Min Act: -0.0001

Data Index: 814624 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.6020. Min Act: -0.0001

Data Index: 722696 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.5504. Min Act: -0.0001

Data Index: 410936 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.9035. Min Range: -0.9035

Max Act: 0.4822. Min Act: -0.0001

Data Index: 101422 (C4 (Web Text))

Max Activating Token Index: 544