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

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

Neuron 147 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: 5.3266. Min Range: -5.3266

Max Act: 5.3266. Min Act: -0.0000

Data Index: 1083851 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 5.3266. Min Range: -5.3266

Max Act: 5.2399. Min Act: -0.0000

Data Index: 1041477 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 5.3266. Min Range: -5.3266

Max Act: 5.2715. Min Act: -0.0000

Data Index: 150582 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 5.3266. Min Range: -5.3266

Max Act: 5.0529. Min Act: -0.0000

Data Index: 1040637 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.1912. Min Act: -0.0000

Data Index: 600718 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.5249. Min Act: -0.0000

Data Index: 213609 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.9207. Min Act: -0.0000

Data Index: 793405 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.2371. Min Act: -0.0000

Data Index: 1317383 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.1823. Min Act: -0.0000

Data Index: 1194724 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.0041. Min Act: -0.0000

Data Index: 935127 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.1187. Min Act: -0.0000

Data Index: 910987 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.0995. Min Act: -0.0000

Data Index: 496981 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.0616. Min Act: -0.0000

Data Index: 1142666 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 5.3266. Min Range: -5.3266

Max Act: 4.0153. Min Act: -0.0000

Data Index: 754232 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.6786. Min Act: -0.0000

Data Index: 728707 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.8225. Min Act: -0.0000

Data Index: 588766 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.6874. Min Act: -0.0000

Data Index: 1196484 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.8005. Min Act: -0.0000

Data Index: 906593 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.7760. Min Act: -0.0000

Data Index: 376049 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 5.3266. Min Range: -5.3266

Max Act: 3.9486. Min Act: -0.0000

Data Index: 552984 (C4 (Web Text))

Max Activating Token Index: 474