Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3366 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.4095. Min Act: -0.0001

Data Index: 400196 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.4094. Min Act: -0.0001

Data Index: 947358 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1051983 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3953. Min Act: -0.0001

Data Index: 875416 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.4323. Min Act: -0.0001

Data Index: 233542 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3747. Min Act: -0.0001

Data Index: 127437 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3760. Min Act: -0.0001

Data Index: 1256486 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.4078. Min Act: -0.0001

Data Index: 1241122 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3905. Min Act: -0.0000

Data Index: 574114 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3746. Min Act: -0.0000

Data Index: 514232 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3550. Min Act: -0.0001

Data Index: 781391 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3643. Min Act: -0.0001

Data Index: 1265289 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3729. Min Act: -0.0001

Data Index: 39694 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3656. Min Act: -0.0000

Data Index: 997625 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3853. Min Act: -0.0001

Data Index: 516635 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3532. Min Act: -0.0001

Data Index: 715295 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3570. Min Act: -0.0001

Data Index: 1328185 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3447. Min Act: -0.0001

Data Index: 494677 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3553. Min Act: -0.0000

Data Index: 422743 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.4657. Min Range: -0.4657

Max Act: 0.3377. Min Act: -0.0000

Data Index: 196214 (C4 (Web Text))

Max Activating Token Index: 703