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

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

Neuron 27 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: 1.9786. Min Range: -1.9786

Max Act: 1.9786. Min Act: -0.0000

Data Index: 1474558 (Python Code)

Max Activating Token Index: 374

Text #1

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.9333. Min Act: -0.0000

Data Index: 1627420 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.9160. Min Act: -0.0000

Data Index: 1416867 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.8068. Min Act: -0.0000

Data Index: 1651177 (Python Code)

Max Activating Token Index: 131

Text #4

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.8833. Min Act: -0.0000

Data Index: 1376558 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.8613. Min Act: -0.0000

Data Index: 1473443 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.7780. Min Act: -0.0000

Data Index: 1425156 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.7256. Min Act: -0.0000

Data Index: 1434032 (Python Code)

Max Activating Token Index: 457

Text #8

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.8247. Min Act: -0.0000

Data Index: 1590966 (Python Code)

Max Activating Token Index: 151

Text #9

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.8463. Min Act: -0.0000

Data Index: 1550602 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.7913. Min Act: -0.0000

Data Index: 1544963 (Python Code)

Max Activating Token Index: 388

Text #11

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.6776. Min Act: -0.0000

Data Index: 1385047 (Python Code)

Max Activating Token Index: 365

Text #12

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.6769. Min Act: -0.0000

Data Index: 1382046 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.8188. Min Act: -0.0000

Data Index: 1635128 (Python Code)

Max Activating Token Index: 950

Text #14

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.6258. Min Act: -0.0000

Data Index: 1422576 (Python Code)

Max Activating Token Index: 360

Text #15

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.7214. Min Act: -0.0000

Data Index: 1542370 (Python Code)

Max Activating Token Index: 237

Text #16

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1524070 (Python Code)

Max Activating Token Index: 461

Text #17

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.7178. Min Act: -0.0000

Data Index: 1467248 (Python Code)

Max Activating Token Index: 320

Text #18

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.7544. Min Act: -0.0000

Data Index: 1407602 (Python Code)

Max Activating Token Index: 502

Text #19

Max Range: 1.9786. Min Range: -1.9786

Max Act: 1.7605. Min Act: -0.0000

Data Index: 1596375 (Python Code)

Max Activating Token Index: 667