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

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

Neuron 5032 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1905. Min Range: -3.1905

Max Act: 3.1905. Min Act: -0.0001

Data Index: 1466526 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 3.1905. Min Range: -3.1905

Max Act: 3.0312. Min Act: -0.0001

Data Index: 1400252 (Python Code)

Max Activating Token Index: 303

Text #2

Max Range: 3.1905. Min Range: -3.1905

Max Act: 3.0071. Min Act: -0.0001

Data Index: 1519569 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.8726. Min Act: -0.0001

Data Index: 1447136 (Python Code)

Max Activating Token Index: 43

Text #4

Max Range: 3.1905. Min Range: -3.1905

Max Act: 3.1034. Min Act: -0.0001

Data Index: 1385154 (Python Code)

Max Activating Token Index: 243

Text #5

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.9585. Min Act: -0.0001

Data Index: 1409851 (Python Code)

Max Activating Token Index: 498

Text #6

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.9485. Min Act: -0.0001

Data Index: 1469351 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.9227. Min Act: -0.0001

Data Index: 1540243 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.9899. Min Act: -0.0001

Data Index: 1585176 (Python Code)

Max Activating Token Index: 58

Text #9

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.8372. Min Act: -0.0001

Data Index: 1433165 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.8295. Min Act: -0.0001

Data Index: 1440158 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.6923. Min Act: -0.0001

Data Index: 1577763 (Python Code)

Max Activating Token Index: 401

Text #12

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.6902. Min Act: -0.0001

Data Index: 1458291 (Python Code)

Max Activating Token Index: 431

Text #13

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.9359. Min Act: -0.0001

Data Index: 1488479 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.7934. Min Act: -0.0001

Data Index: 1466437 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.7995. Min Act: -0.0001

Data Index: 1390581 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.8143. Min Act: -0.0001

Data Index: 1398858 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.8013. Min Act: -0.0001

Data Index: 1583825 (Python Code)

Max Activating Token Index: 396

Text #18

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.7848. Min Act: -0.0001

Data Index: 1626544 (Python Code)

Max Activating Token Index: 527

Text #19

Max Range: 3.1905. Min Range: -3.1905

Max Act: 2.8844. Min Act: -0.0001

Data Index: 1504231 (Python Code)

Max Activating Token Index: 65