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

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

Neuron 2307 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: 1.9095. Min Range: -1.9095

Max Act: 1.9095. Min Act: -0.0001

Data Index: 1574791 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.5468. Min Act: -0.0001

Data Index: 1512961 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.4817. Min Act: -0.0001

Data Index: 1591141 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.3107. Min Act: -0.0001

Data Index: 1537197 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.3573. Min Act: -0.0001

Data Index: 1504927 (Python Code)

Max Activating Token Index: 667

Text #5

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2814. Min Act: -0.0001

Data Index: 1633103 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2776. Min Act: -0.0001

Data Index: 1358115 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2792. Min Act: -0.0001

Data Index: 13488 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2454. Min Act: -0.0001

Data Index: 1594246 (Python Code)

Max Activating Token Index: 521

Text #9

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2600. Min Act: -0.0001

Data Index: 1610378 (Python Code)

Max Activating Token Index: 7

Text #10

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2124. Min Act: -0.0001

Data Index: 1626738 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2446. Min Act: -0.0001

Data Index: 1457477 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2710. Min Act: -0.0001

Data Index: 1440839 (Python Code)

Max Activating Token Index: 8

Text #13

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2186. Min Act: -0.0001

Data Index: 1451051 (Python Code)

Max Activating Token Index: 431

Text #14

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.1650. Min Act: -0.0001

Data Index: 1361553 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.2473. Min Act: -0.0001

Data Index: 1409212 (Python Code)

Max Activating Token Index: 704

Text #16

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.1826. Min Act: -0.0001

Data Index: 1396812 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.1627. Min Act: -0.0001

Data Index: 1603454 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.1164. Min Act: -0.0001

Data Index: 1492177 (Python Code)

Max Activating Token Index: 364

Text #19

Max Range: 1.9095. Min Range: -1.9095

Max Act: 1.0944. Min Act: -0.0001

Data Index: 1414133 (Python Code)

Max Activating Token Index: 650