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

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

Neuron 4506 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7919. Min Range: -4.7919

Max Act: 4.7919. Min Act: -0.0000

Data Index: 1448822 (Python Code)

Max Activating Token Index: 188

Text #1

Max Range: 4.7919. Min Range: -4.7919

Max Act: 4.0436. Min Act: -0.0000

Data Index: 1591535 (Python Code)

Max Activating Token Index: 545

Text #2

Max Range: 4.7919. Min Range: -4.7919

Max Act: 4.2189. Min Act: -0.0000

Data Index: 1501478 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 4.7919. Min Range: -4.7919

Max Act: 4.4309. Min Act: -0.0000

Data Index: 1407788 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 4.7919. Min Range: -4.7919

Max Act: 4.3745. Min Act: -0.0000

Data Index: 1361841 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 4.7919. Min Range: -4.7919

Max Act: 4.1374. Min Act: -0.0000

Data Index: 1530543 (Python Code)

Max Activating Token Index: 573

Text #6

Max Range: 4.7919. Min Range: -4.7919

Max Act: 4.0990. Min Act: -0.0001

Data Index: 1486894 (Python Code)

Max Activating Token Index: 408

Text #7

Max Range: 4.7919. Min Range: -4.7919

Max Act: 4.0931. Min Act: -0.0000

Data Index: 1571124 (Python Code)

Max Activating Token Index: 854

Text #8

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.8168. Min Act: -0.0000

Data Index: 1377603 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.9151. Min Act: -0.0000

Data Index: 1588514 (Python Code)

Max Activating Token Index: 854

Text #10

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.8917. Min Act: -0.0000

Data Index: 1633844 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.8948. Min Act: -0.0000

Data Index: 1464495 (Python Code)

Max Activating Token Index: 672

Text #12

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.6816. Min Act: -0.0000

Data Index: 1480008 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.8432. Min Act: -0.0000

Data Index: 1375840 (Python Code)

Max Activating Token Index: 453

Text #14

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.9135. Min Act: -0.0000

Data Index: 1507246 (Python Code)

Max Activating Token Index: 1018

Text #15

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.5817. Min Act: -0.0000

Data Index: 1477297 (Python Code)

Max Activating Token Index: 808

Text #16

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.5507. Min Act: -0.0000

Data Index: 1370178 (Python Code)

Max Activating Token Index: 69

Text #17

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.7091. Min Act: -0.0000

Data Index: 1531171 (Python Code)

Max Activating Token Index: 644

Text #18

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.7385. Min Act: -0.0000

Data Index: 1477528 (Python Code)

Max Activating Token Index: 199

Text #19

Max Range: 4.7919. Min Range: -4.7919

Max Act: 3.6809. Min Act: -0.0000

Data Index: 1471807 (Python Code)

Max Activating Token Index: 426