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

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

Neuron 3473 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.6296. Min Act: -0.0000

Data Index: 1438328 (Python Code)

Max Activating Token Index: 466

Text #1

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.5455. Min Act: -0.0000

Data Index: 1573172 (Python Code)

Max Activating Token Index: 853

Text #2

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.5722. Min Act: -0.0000

Data Index: 1552771 (Python Code)

Max Activating Token Index: 682

Text #3

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.4946. Min Act: -0.0000

Data Index: 1585005 (Python Code)

Max Activating Token Index: 101

Text #4

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.3470. Min Act: -0.0000

Data Index: 1540885 (Python Code)

Max Activating Token Index: 942

Text #5

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.4262. Min Act: -0.0000

Data Index: 586820 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.2614. Min Act: -0.0000

Data Index: 1566116 (Python Code)

Max Activating Token Index: 685

Text #7

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.3901. Min Act: -0.0000

Data Index: 1429024 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1404914 (Python Code)

Max Activating Token Index: 496

Text #9

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1561430 (Python Code)

Max Activating Token Index: 467

Text #10

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1521390 (Python Code)

Max Activating Token Index: 976

Text #11

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.3004. Min Act: -0.0000

Data Index: 1419924 (Python Code)

Max Activating Token Index: 326

Text #12

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.2939. Min Act: -0.0000

Data Index: 1483923 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1446815 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.3126. Min Act: -0.0000

Data Index: 1472522 (Python Code)

Max Activating Token Index: 436

Text #15

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.2798. Min Act: -0.0000

Data Index: 1506710 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.3024. Min Act: -0.0000

Data Index: 1575689 (Python Code)

Max Activating Token Index: 477

Text #17

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.2505. Min Act: -0.0000

Data Index: 1496769 (Python Code)

Max Activating Token Index: 760

Text #18

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.2136. Min Act: -0.0000

Data Index: 1617461 (Python Code)

Max Activating Token Index: 710

Text #19

Max Range: 1.6296. Min Range: -1.6296

Max Act: 1.2298. Min Act: -0.0000

Data Index: 876557 (C4 (Web Text))

Max Activating Token Index: 545