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

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

Neuron 4065 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1064. Min Range: -1.1064

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1569136 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 1.1064. Min Range: -1.1064

Max Act: 1.0556. Min Act: -0.0000

Data Index: 1378830 (Python Code)

Max Activating Token Index: 224

Text #2

Max Range: 1.1064. Min Range: -1.1064

Max Act: 1.0521. Min Act: -0.0000

Data Index: 1599598 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 1.1064. Min Range: -1.1064

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1586515 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8838. Min Act: -0.0000

Data Index: 1636104 (Python Code)

Max Activating Token Index: 235

Text #5

Max Range: 1.1064. Min Range: -1.1064

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1534757 (Python Code)

Max Activating Token Index: 94

Text #6

Max Range: 1.1064. Min Range: -1.1064

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1652358 (Python Code)

Max Activating Token Index: 800

Text #7

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1440812 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1582215 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9654. Min Act: -0.0000

Data Index: 1636055 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1377241 (Python Code)

Max Activating Token Index: 716

Text #11

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1464320 (Python Code)

Max Activating Token Index: 933

Text #12

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9073. Min Act: -0.0001

Data Index: 1512925 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1502424 (Python Code)

Max Activating Token Index: 279

Text #14

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1374094 (Python Code)

Max Activating Token Index: 271

Text #15

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1534657 (Python Code)

Max Activating Token Index: 298

Text #16

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1635831 (Python Code)

Max Activating Token Index: 503

Text #17

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1589613 (Python Code)

Max Activating Token Index: 483

Text #18

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1649156 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 1.1064. Min Range: -1.1064

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1536794 (Python Code)

Max Activating Token Index: 124