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

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

Neuron 1924 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: 2.2702. Min Range: -2.2702

Max Act: 2.2702. Min Act: -0.0000

Data Index: 400273 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 2.2702. Min Range: -2.2702

Max Act: 2.0664. Min Act: -0.0000

Data Index: 576330 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.7818. Min Act: -0.0000

Data Index: 1184781 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.6478. Min Act: -0.0000

Data Index: 69352 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.8172. Min Act: -0.0000

Data Index: 1187918 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.6882. Min Act: -0.0000

Data Index: 699432 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.5795. Min Act: -0.0000

Data Index: 1213311 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.3855. Min Act: -0.0000

Data Index: 1166244 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1228790 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.3936. Min Act: 0.0000

Data Index: 1460284 (Python Code)

Max Activating Token Index: 713

Text #10

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.4697. Min Act: -0.0000

Data Index: 9416 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.2788. Min Act: -0.0000

Data Index: 245478 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.3093. Min Act: -0.0000

Data Index: 212851 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.2414. Min Act: -0.0000

Data Index: 305018 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.2916. Min Act: -0.0000

Data Index: 544230 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.2581. Min Act: -0.0000

Data Index: 658911 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.2561. Min Act: 0.0001

Data Index: 1584926 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.2411. Min Act: 0.0001

Data Index: 1584848 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.2409. Min Act: -0.0000

Data Index: 951934 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 2.2702. Min Range: -2.2702

Max Act: 1.2199. Min Act: -0.0000

Data Index: 893796 (C4 (Web Text))

Max Activating Token Index: 746