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

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

Neuron 4885 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: 2.6606. Min Range: -2.6606

Max Act: 2.6606. Min Act: -0.0000

Data Index: 713946 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.5475. Min Act: -0.0000

Data Index: 1290549 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.2081. Min Act: -0.0000

Data Index: 480401 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.0539. Min Act: -0.0000

Data Index: 1221586 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.1405. Min Act: -0.0000

Data Index: 1123032 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.2243. Min Act: -0.0000

Data Index: 558873 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.1676. Min Act: -0.0000

Data Index: 892002 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.0570. Min Act: -0.0000

Data Index: 741647 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 2.6606. Min Range: -2.6606

Max Act: 1.9200. Min Act: -0.0000

Data Index: 95975 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.0314. Min Act: -0.0000

Data Index: 128816 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.1373. Min Act: -0.0000

Data Index: 588918 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.0195. Min Act: -0.0000

Data Index: 523992 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 2.6606. Min Range: -2.6606

Max Act: 2.0995. Min Act: -0.0000

Data Index: 1089357 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 2.6606. Min Range: -2.6606

Max Act: 1.9932. Min Act: -0.0000

Data Index: 97877 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 2.6606. Min Range: -2.6606

Max Act: 1.9183. Min Act: -0.0000

Data Index: 567995 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 2.6606. Min Range: -2.6606

Max Act: 1.9178. Min Act: -0.0000

Data Index: 33197 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 2.6606. Min Range: -2.6606

Max Act: 1.9391. Min Act: -0.0000

Data Index: 995390 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 2.6606. Min Range: -2.6606

Max Act: 1.9210. Min Act: -0.0000

Data Index: 543248 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 2.6606. Min Range: -2.6606

Max Act: 1.8820. Min Act: -0.0000

Data Index: 691397 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 2.6606. Min Range: -2.6606

Max Act: 1.8780. Min Act: -0.0000

Data Index: 1059980 (C4 (Web Text))

Max Activating Token Index: 975