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

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

Neuron 2941 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9876. Min Range: -5.9876

Max Act: 5.9876. Min Act: 0.0001

Data Index: 832107 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 5.9876. Min Range: -5.9876

Max Act: 5.2502. Min Act: 0.0000

Data Index: 1180474 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 5.9876. Min Range: -5.9876

Max Act: 5.0286. Min Act: -0.0000

Data Index: 749267 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.6014. Min Act: -0.0000

Data Index: 162240 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.9774. Min Act: -0.0000

Data Index: 703792 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.7342. Min Act: -0.0000

Data Index: 480719 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.2990. Min Act: 0.0001

Data Index: 1026791 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.6102. Min Act: -0.0000

Data Index: 400130 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.5390. Min Act: -0.0000

Data Index: 111455 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.2380. Min Act: -0.0000

Data Index: 1055295 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.0592. Min Act: -0.0000

Data Index: 455924 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.2218. Min Act: -0.0000

Data Index: 662610 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.3675. Min Act: -0.0000

Data Index: 899443 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 5.9876. Min Range: -5.9876

Max Act: 3.8446. Min Act: 0.0000

Data Index: 1042143 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.3294. Min Act: -0.0000

Data Index: 406966 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.1652. Min Act: 0.0001

Data Index: 1172912 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 5.9876. Min Range: -5.9876

Max Act: 3.9692. Min Act: -0.0000

Data Index: 559175 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.1110. Min Act: -0.0000

Data Index: 65180 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.0896. Min Act: -0.0000

Data Index: 783444 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 5.9876. Min Range: -5.9876

Max Act: 4.0495. Min Act: 0.0000

Data Index: 809161 (C4 (Web Text))

Max Activating Token Index: 586