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

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

Neuron 4452 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.4228. Min Act: -0.0000

Data Index: 1549563 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.3730. Min Act: 0.0000

Data Index: 1482890 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.3912. Min Act: -0.0000

Data Index: 1390086 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.1979. Min Act: -0.0000

Data Index: 1629778 (Python Code)

Max Activating Token Index: 69

Text #4

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1654684 (Python Code)

Max Activating Token Index: 392

Text #5

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.3156. Min Act: -0.0000

Data Index: 1598035 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.3790. Min Act: 0.0001

Data Index: 1383030 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1461863 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1360728 (Python Code)

Max Activating Token Index: 456

Text #9

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0928. Min Act: -0.0000

Data Index: 1496968 (Python Code)

Max Activating Token Index: 299

Text #10

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.1533. Min Act: -0.0000

Data Index: 1578061 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.1863. Min Act: 0.0000

Data Index: 1441819 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1479856 (Python Code)

Max Activating Token Index: 692

Text #13

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1532979 (Python Code)

Max Activating Token Index: 299

Text #14

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1651040 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9810. Min Act: 0.0000

Data Index: 1370358 (Python Code)

Max Activating Token Index: 818

Text #16

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0155. Min Act: -0.0000

Data Index: 1566216 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 1.4228. Min Range: -1.4228

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1395608 (Python Code)

Max Activating Token Index: 929

Text #18

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1504384 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 1.4228. Min Range: -1.4228

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1375169 (Python Code)

Max Activating Token Index: 135