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

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

Neuron 1248 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3681. Min Range: -2.3681

Max Act: 2.3681. Min Act: -0.0000

Data Index: 1624686 (Python Code)

Max Activating Token Index: 624

Text #1

Max Range: 2.3681. Min Range: -2.3681

Max Act: 2.1041. Min Act: -0.0000

Data Index: 1656927 (Python Code)

Max Activating Token Index: 885

Text #2

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.9543. Min Act: -0.0000

Data Index: 1601601 (Python Code)

Max Activating Token Index: 945

Text #3

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.6391. Min Act: -0.0000

Data Index: 1437370 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.5744. Min Act: -0.0000

Data Index: 1578073 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.3719. Min Act: 0.0000

Data Index: 1506531 (Python Code)

Max Activating Token Index: 226

Text #6

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1531797 (Python Code)

Max Activating Token Index: 761

Text #7

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.1907. Min Act: 0.0000

Data Index: 1411158 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.0869. Min Act: -0.0000

Data Index: 1495072 (Python Code)

Max Activating Token Index: 795

Text #9

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.2386. Min Act: 0.0000

Data Index: 1622730 (Python Code)

Max Activating Token Index: 918

Text #10

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.1521. Min Act: 0.0000

Data Index: 1628440 (Python Code)

Max Activating Token Index: 796

Text #11

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.1261. Min Act: 0.0000

Data Index: 1362623 (Python Code)

Max Activating Token Index: 513

Text #12

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.0993. Min Act: 0.0000

Data Index: 1476003 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.1239. Min Act: 0.0000

Data Index: 1582451 (Python Code)

Max Activating Token Index: 136

Text #14

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1423517 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1525421 (Python Code)

Max Activating Token Index: 457

Text #16

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1491780 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.0301. Min Act: -0.0000

Data Index: 1432186 (Python Code)

Max Activating Token Index: 284

Text #18

Max Range: 2.3681. Min Range: -2.3681

Max Act: 1.0562. Min Act: -0.0000

Data Index: 1432711 (Python Code)

Max Activating Token Index: 700

Text #19

Max Range: 2.3681. Min Range: -2.3681

Max Act: 0.9773. Min Act: -0.0000

Data Index: 1386018 (Python Code)

Max Activating Token Index: 762