Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1692 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0034. Min Act: -0.0006

Data Index: 1440630 (Python Code)

Max Activating Token Index: 30

Text #1

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0033. Min Act: -0.0005

Data Index: 1401982 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0033. Min Act: -0.0006

Data Index: 1630000 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0033. Min Act: -0.0005

Data Index: 1420256 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0006

Data Index: 1460740 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1521622 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0006

Data Index: 1656049 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1490992 (Python Code)

Max Activating Token Index: 79

Text #8

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1593354 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1373594 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0006

Data Index: 1558535 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1482507 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0030. Min Act: -0.0006

Data Index: 1344194 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0006

Data Index: 1535937 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1387233 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1434865 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0030. Min Act: -0.0006

Data Index: 1323950 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1454613 (Python Code)

Max Activating Token Index: 63

Text #18

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0030. Min Act: -0.0006

Data Index: 1476034 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.0034. Min Range: -0.0034

Max Act: 0.0030. Min Act: -0.0006

Data Index: 1364565 (Python Code)

Max Activating Token Index: 10