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

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

Neuron 2460 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0954. Min Range: -3.0954

Max Act: 3.0954. Min Act: -0.0000

Data Index: 444880 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.8420. Min Act: -0.0000

Data Index: 807587 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.3390. Min Act: -0.0000

Data Index: 594668 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.2706. Min Act: -0.0000

Data Index: 1160557 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.2129. Min Act: -0.0000

Data Index: 882747 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.1746. Min Act: -0.0000

Data Index: 1030392 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.2683. Min Act: -0.0000

Data Index: 923146 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.0750. Min Act: -0.0000

Data Index: 136972 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.0620. Min Act: -0.0000

Data Index: 322472 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 3.0954. Min Range: -3.0954

Max Act: 1.9541. Min Act: -0.0000

Data Index: 243311 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.1723. Min Act: -0.0000

Data Index: 172468 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.0390. Min Act: -0.0000

Data Index: 926442 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.0282. Min Act: -0.0000

Data Index: 1077977 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.1232. Min Act: -0.0000

Data Index: 1225565 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.0100. Min Act: -0.0000

Data Index: 1097274 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 3.0954. Min Range: -3.0954

Max Act: 1.8826. Min Act: -0.0000

Data Index: 377085 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 3.0954. Min Range: -3.0954

Max Act: 1.8994. Min Act: -0.0000

Data Index: 1313020 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 3.0954. Min Range: -3.0954

Max Act: 1.9817. Min Act: -0.0000

Data Index: 221649 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 3.0954. Min Range: -3.0954

Max Act: 2.0969. Min Act: -0.0000

Data Index: 814772 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 3.0954. Min Range: -3.0954

Max Act: 1.9803. Min Act: -0.0000

Data Index: 708214 (C4 (Web Text))

Max Activating Token Index: 422