Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 900 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 5.7088. Min Range: -5.7088

Max Act: 5.7088. Min Act: -0.0001

Data Index: 1540660 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 5.7088. Min Range: -5.7088

Max Act: 4.2332. Min Act: -0.0001

Data Index: 1627766 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 5.7088. Min Range: -5.7088

Max Act: 4.1303. Min Act: -0.0001

Data Index: 1626819 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 5.7088. Min Range: -5.7088

Max Act: 3.6437. Min Act: -0.0001

Data Index: 1475828 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 5.7088. Min Range: -5.7088

Max Act: 3.4485. Min Act: -0.0001

Data Index: 1492583 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 5.7088. Min Range: -5.7088

Max Act: 3.1083. Min Act: -0.0001

Data Index: 1413631 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 5.7088. Min Range: -5.7088

Max Act: 3.3731. Min Act: -0.0001

Data Index: 1475524 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 5.7088. Min Range: -5.7088

Max Act: 3.4655. Min Act: -0.0001

Data Index: 1564848 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 5.7088. Min Range: -5.7088

Max Act: 2.6527. Min Act: -0.0001

Data Index: 1648682 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 5.7088. Min Range: -5.7088

Max Act: 3.0865. Min Act: -0.0001

Data Index: 1615038 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 5.7088. Min Range: -5.7088

Max Act: 2.3043. Min Act: -0.0001

Data Index: 1535843 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 5.7088. Min Range: -5.7088

Max Act: 2.1879. Min Act: -0.0001

Data Index: 1452589 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 5.7088. Min Range: -5.7088

Max Act: 2.1106. Min Act: -0.0001

Data Index: 1541309 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 5.7088. Min Range: -5.7088

Max Act: 2.0119. Min Act: -0.0001

Data Index: 1650863 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 5.7088. Min Range: -5.7088

Max Act: 2.5080. Min Act: -0.0001

Data Index: 1484051 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 5.7088. Min Range: -5.7088

Max Act: 1.8900. Min Act: -0.0001

Data Index: 1362538 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 5.7088. Min Range: -5.7088

Max Act: 2.2197. Min Act: -0.0001

Data Index: 1624730 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 5.7088. Min Range: -5.7088

Max Act: 2.0931. Min Act: -0.0001

Data Index: 1442129 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 5.7088. Min Range: -5.7088

Max Act: 1.8759. Min Act: -0.0001

Data Index: 1553575 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 5.7088. Min Range: -5.7088

Max Act: 2.0135. Min Act: -0.0001

Data Index: 1369430 (Python Code)

Max Activating Token Index: 1023