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

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

Neuron 1592 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1584413 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1415140 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1547508 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1481005 (Python Code)

Max Activating Token Index: 144

Text #4

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1463691 (Python Code)

Max Activating Token Index: 894

Text #5

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1636768 (Python Code)

Max Activating Token Index: 286

Text #6

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1652684 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1585070 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1371225 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1588946 (Python Code)

Max Activating Token Index: 830

Text #10

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1634602 (Python Code)

Max Activating Token Index: 163

Text #11

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1557649 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1865. Min Act: -0.0001

Data Index: 1466169 (Python Code)

Max Activating Token Index: 868

Text #13

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1360449 (Python Code)

Max Activating Token Index: 214

Text #14

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1562477 (Python Code)

Max Activating Token Index: 685

Text #15

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1569071 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1504028 (Python Code)

Max Activating Token Index: 582

Text #17

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1587681 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1538402 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 0.2936. Min Range: -0.2936

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1493800 (Python Code)

Max Activating Token Index: 89