Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 312 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.6776. Min Act: -0.0000

Data Index: 47518 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.6313. Min Act: -0.0000

Data Index: 339354 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.5447. Min Act: -0.0001

Data Index: 1307594 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.3960. Min Act: -0.0001

Data Index: 1075297 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1325230 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.2578. Min Act: -0.0000

Data Index: 179731 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.2384. Min Act: -0.0000

Data Index: 161788 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.3357. Min Act: -0.0001

Data Index: 1211537 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.2425. Min Act: -0.0000

Data Index: 388995 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.2414. Min Act: -0.0001

Data Index: 507527 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.2702. Min Act: -0.0000

Data Index: 636116 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.2405. Min Act: -0.0000

Data Index: 421905 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.1841. Min Act: -0.0001

Data Index: 335428 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.1430. Min Act: -0.0000

Data Index: 995207 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.1023. Min Act: -0.0000

Data Index: 888598 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.2205. Min Act: -0.0000

Data Index: 566465 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.0710. Min Act: -0.0000

Data Index: 131219 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.1216. Min Act: -0.0000

Data Index: 319588 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.0916. Min Act: -0.0000

Data Index: 372889 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 1.6776. Min Range: -1.6776

Max Act: 1.1893. Min Act: -0.0000

Data Index: 256136 (C4 (Web Text))

Max Activating Token Index: 142