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

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

Neuron 1950 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9332. Min Range: -2.9332

Max Act: 2.9332. Min Act: -0.0000

Data Index: 745047 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 2.9332. Min Range: -2.9332

Max Act: 2.3780. Min Act: -0.0000

Data Index: 551692 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 2.9332. Min Range: -2.9332

Max Act: 2.3241. Min Act: -0.0000

Data Index: 659527 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.9998. Min Act: -0.0000

Data Index: 1176393 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.5664. Min Act: -0.0000

Data Index: 373363 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.5195. Min Act: -0.0000

Data Index: 956419 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.4217. Min Act: -0.0000

Data Index: 1346810 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.3172. Min Act: -0.0000

Data Index: 146457 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.3500. Min Act: -0.0000

Data Index: 162478 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.3577. Min Act: -0.0000

Data Index: 38427 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.2733. Min Act: -0.0000

Data Index: 486141 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1104762 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.2366. Min Act: -0.0000

Data Index: 681609 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1164953 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.1969. Min Act: -0.0000

Data Index: 507099 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.1900. Min Act: -0.0000

Data Index: 971858 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.2610. Min Act: -0.0000

Data Index: 639204 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.2432. Min Act: -0.0000

Data Index: 801842 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.2385. Min Act: -0.0000

Data Index: 734393 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 2.9332. Min Range: -2.9332

Max Act: 1.2773. Min Act: -0.0000

Data Index: 183866 (C4 (Web Text))

Max Activating Token Index: 245