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

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

Neuron 3194 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.6508. Min Act: -0.0000

Data Index: 1539379 (Python Code)

Max Activating Token Index: 411

Text #1

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1532144 (Python Code)

Max Activating Token Index: 797

Text #2

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1466992 (Python Code)

Max Activating Token Index: 224

Text #3

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1647468 (Python Code)

Max Activating Token Index: 229

Text #4

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5641. Min Act: -0.0000

Data Index: 1398504 (Python Code)

Max Activating Token Index: 833

Text #5

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1620394 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1599380 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1574955 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1503015 (Python Code)

Max Activating Token Index: 253

Text #9

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1360714 (Python Code)

Max Activating Token Index: 279

Text #10

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1622045 (Python Code)

Max Activating Token Index: 507

Text #11

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1654473 (Python Code)

Max Activating Token Index: 344

Text #12

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1590612 (Python Code)

Max Activating Token Index: 284

Text #13

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1381568 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1430878 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1632472 (Python Code)

Max Activating Token Index: 514

Text #16

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1605389 (Python Code)

Max Activating Token Index: 194

Text #17

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1468082 (Python Code)

Max Activating Token Index: 790

Text #18

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1385869 (Python Code)

Max Activating Token Index: 367

Text #19

Max Range: 0.6508. Min Range: -0.6508

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1612891 (Python Code)

Max Activating Token Index: 961