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

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

Neuron 4394 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1750. Min Act: -0.0001

Data Index: 80218 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1492. Min Act: -0.0001

Data Index: 817688 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1492. Min Act: -0.0001

Data Index: 312413 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1458. Min Act: -0.0001

Data Index: 942050 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1442. Min Act: -0.0001

Data Index: 425720 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1020582 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1320. Min Act: -0.0001

Data Index: 194064 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1509283 (Python Code)

Max Activating Token Index: 740

Text #8

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1391650 (Python Code)

Max Activating Token Index: 632

Text #9

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1536. Min Act: -0.0001

Data Index: 113829 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1489. Min Act: -0.0001

Data Index: 565914 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1361. Min Act: -0.0001

Data Index: 843635 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1347. Min Act: -0.0001

Data Index: 729996 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1373. Min Act: -0.0001

Data Index: 1392011 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1337. Min Act: -0.0001

Data Index: 938936 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1491503 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1344. Min Act: -0.0001

Data Index: 916362 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1360. Min Act: -0.0001

Data Index: 227213 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1376. Min Act: -0.0001

Data Index: 775762 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.1750. Min Range: -0.1750

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1558238 (Python Code)

Max Activating Token Index: 406