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

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

Neuron 1464 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1641. Min Range: -3.1641

Max Act: 3.0394. Min Act: -0.0000

Data Index: 1432258 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.9472. Min Act: -0.0000

Data Index: 1406601 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.6740. Min Act: -0.0000

Data Index: 1362400 (Python Code)

Max Activating Token Index: 808

Text #3

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.9276. Min Act: -0.0000

Data Index: 1473830 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.7516. Min Act: -0.0000

Data Index: 1361686 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 3.1641. Min Range: -3.1641

Max Act: 3.1641. Min Act: -0.0000

Data Index: 1381893 (Python Code)

Max Activating Token Index: 833

Text #6

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.8849. Min Act: -0.0000

Data Index: 1373140 (Python Code)

Max Activating Token Index: 815

Text #7

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.8217. Min Act: -0.0000

Data Index: 1618276 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.6679. Min Act: -0.0000

Data Index: 1485742 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.6588. Min Act: -0.0000

Data Index: 1505132 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.6527. Min Act: -0.0000

Data Index: 1544868 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.9108. Min Act: -0.0000

Data Index: 1645683 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.5071. Min Act: -0.0000

Data Index: 1651082 (Python Code)

Max Activating Token Index: 151

Text #13

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.7249. Min Act: -0.0000

Data Index: 1575526 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.5763. Min Act: -0.0000

Data Index: 1524372 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.4321. Min Act: -0.0000

Data Index: 1521123 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.5386. Min Act: -0.0000

Data Index: 1508203 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.6688. Min Act: -0.0000

Data Index: 1376308 (Python Code)

Max Activating Token Index: 142

Text #18

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.5474. Min Act: -0.0000

Data Index: 1463885 (Python Code)

Max Activating Token Index: 64

Text #19

Max Range: 3.1641. Min Range: -3.1641

Max Act: 2.6477. Min Act: -0.0000

Data Index: 1544298 (Python Code)

Max Activating Token Index: 127