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

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

Neuron 5109 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1517567 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3896. Min Act: -0.0000

Data Index: 1535549 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1440055 (Python Code)

Max Activating Token Index: 738

Text #3

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1556302 (Python Code)

Max Activating Token Index: 462

Text #4

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1273780 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1427283 (Python Code)

Max Activating Token Index: 1011

Text #6

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1370872 (Python Code)

Max Activating Token Index: 129

Text #7

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0663. Min Act: -0.0000

Data Index: 1531215 (Python Code)

Max Activating Token Index: 557

Text #8

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0731. Min Act: 0.0000

Data Index: 1478753 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0627. Min Act: 0.0000

Data Index: 1528566 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1553356 (Python Code)

Max Activating Token Index: 507

Text #11

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1512767 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1615175 (Python Code)

Max Activating Token Index: 204

Text #13

Max Range: 1.3896. Min Range: -1.3896

Max Act: 0.9715. Min Act: -0.0000

Data Index: 1365128 (Python Code)

Max Activating Token Index: 882

Text #14

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1368336 (Python Code)

Max Activating Token Index: 815

Text #15

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1411628 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1386817 (Python Code)

Max Activating Token Index: 412

Text #17

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1569006 (Python Code)

Max Activating Token Index: 423

Text #18

Max Range: 1.3896. Min Range: -1.3896

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1568096 (Python Code)

Max Activating Token Index: 948

Text #19

Max Range: 1.3896. Min Range: -1.3896

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1565962 (Python Code)

Max Activating Token Index: 339