Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3513 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1531079 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5902. Min Act: -0.0001

Data Index: 1446446 (Python Code)

Max Activating Token Index: 437

Text #2

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6258. Min Act: -0.0001

Data Index: 1450841 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4931. Min Act: -0.0001

Data Index: 1506643 (Python Code)

Max Activating Token Index: 248

Text #4

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4603. Min Act: -0.0001

Data Index: 1618758 (Python Code)

Max Activating Token Index: 479

Text #5

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4401. Min Act: -0.0001

Data Index: 1565155 (Python Code)

Max Activating Token Index: 116

Text #6

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.5294. Min Act: -0.0001

Data Index: 1625216 (Python Code)

Max Activating Token Index: 709

Text #7

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4449. Min Act: -0.0001

Data Index: 1554116 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4387. Min Act: -0.0001

Data Index: 1563390 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4755. Min Act: -0.0001

Data Index: 1390892 (Python Code)

Max Activating Token Index: 208

Text #10

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4563. Min Act: -0.0001

Data Index: 1166564 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1434190 (Python Code)

Max Activating Token Index: 345

Text #12

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4589. Min Act: -0.0001

Data Index: 1424842 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4302. Min Act: -0.0001

Data Index: 1610670 (Python Code)

Max Activating Token Index: 209

Text #14

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4480. Min Act: -0.0001

Data Index: 1594834 (Python Code)

Max Activating Token Index: 109

Text #15

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4346. Min Act: -0.0001

Data Index: 88120 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4382. Min Act: -0.0001

Data Index: 1448782 (Python Code)

Max Activating Token Index: 64

Text #17

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4251. Min Act: -0.0001

Data Index: 1431792 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4525. Min Act: -0.0001

Data Index: 1501227 (Python Code)

Max Activating Token Index: 215

Text #19

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1456559 (Python Code)

Max Activating Token Index: 749