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

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

Neuron 3268 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.2447. Min Act: -0.0002

Data Index: 1029815 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.2271. Min Act: -0.0002

Data Index: 1624160 (Python Code)

Max Activating Token Index: 810

Text #2

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1871. Min Act: -0.0002

Data Index: 1577639 (Python Code)

Max Activating Token Index: 896

Text #3

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1569. Min Act: -0.0002

Data Index: 1520549 (Python Code)

Max Activating Token Index: 755

Text #4

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1666. Min Act: -0.0002

Data Index: 1560779 (Python Code)

Max Activating Token Index: 780

Text #5

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1517. Min Act: -0.0002

Data Index: 138953 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1368. Min Act: -0.0002

Data Index: 1185829 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1202. Min Act: -0.0002

Data Index: 1494589 (Python Code)

Max Activating Token Index: 668

Text #8

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1377. Min Act: -0.0002

Data Index: 1453515 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1364. Min Act: -0.0002

Data Index: 1381071 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1012. Min Act: -0.0002

Data Index: 1533938 (Python Code)

Max Activating Token Index: 644

Text #11

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1270. Min Act: -0.0002

Data Index: 1228727 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1046. Min Act: -0.0002

Data Index: 1646491 (Python Code)

Max Activating Token Index: 442

Text #13

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.1280. Min Act: -0.0002

Data Index: 1383944 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.0972. Min Act: -0.0002

Data Index: 1625182 (Python Code)

Max Activating Token Index: 633

Text #15

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.0746. Min Act: -0.0002

Data Index: 1597940 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.0653. Min Act: -0.0002

Data Index: 1586670 (Python Code)

Max Activating Token Index: 972

Text #17

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.0429. Min Act: -0.0002

Data Index: 1559296 (Python Code)

Max Activating Token Index: 651

Text #18

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.0702. Min Act: -0.0002

Data Index: 1433031 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 1.2447. Min Range: -1.2447

Max Act: 1.0825. Min Act: -0.0002

Data Index: 1387978 (Python Code)

Max Activating Token Index: 547