Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1592 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0001. Min Range: -2.0001

Max Act: 2.0001. Min Act: 0.0000

Data Index: 537487 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.8779. Min Act: -0.0000

Data Index: 94122 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.9647. Min Act: -0.0000

Data Index: 1107649 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.7089. Min Act: -0.0000

Data Index: 1311146 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.7134. Min Act: -0.0000

Data Index: 1294272 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5973. Min Act: -0.0000

Data Index: 868871 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5829. Min Act: -0.0000

Data Index: 755213 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6690. Min Act: -0.0000

Data Index: 53760 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4868. Min Act: 0.0000

Data Index: 726654 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.6391. Min Act: -0.0000

Data Index: 76861 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5357. Min Act: 0.0000

Data Index: 676405 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.5323. Min Act: -0.0000

Data Index: 480182 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1294442 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4641. Min Act: 0.0000

Data Index: 886858 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1150252 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4301. Min Act: -0.0000

Data Index: 329470 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4151. Min Act: -0.0000

Data Index: 835229 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.4751. Min Act: -0.0000

Data Index: 180836 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3858. Min Act: 0.0000

Data Index: 334364 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 2.0001. Min Range: -2.0001

Max Act: 1.3834. Min Act: -0.0000

Data Index: 1027738 (C4 (Web Text))

Max Activating Token Index: 359