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

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

Neuron 3177 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1645911 (Python Code)

Max Activating Token Index: 244

Text #1

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1454941 (Python Code)

Max Activating Token Index: 396

Text #2

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1610265 (Python Code)

Max Activating Token Index: 211

Text #3

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1624269 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1539862 (Python Code)

Max Activating Token Index: 835

Text #5

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1530930 (Python Code)

Max Activating Token Index: 683

Text #6

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1501128 (Python Code)

Max Activating Token Index: 799

Text #7

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1649802 (Python Code)

Max Activating Token Index: 183

Text #8

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7659. Min Act: -0.0001

Data Index: 1466785 (Python Code)

Max Activating Token Index: 888

Text #9

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7520. Min Act: -0.0001

Data Index: 1644494 (Python Code)

Max Activating Token Index: 508

Text #10

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6929. Min Act: -0.0001

Data Index: 1596847 (Python Code)

Max Activating Token Index: 1021

Text #11

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7291. Min Act: -0.0001

Data Index: 1512862 (Python Code)

Max Activating Token Index: 722

Text #12

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7505. Min Act: -0.0001

Data Index: 1553328 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1463126 (Python Code)

Max Activating Token Index: 1004

Text #14

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1564136 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6920. Min Act: -0.0001

Data Index: 1518256 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1398431 (Python Code)

Max Activating Token Index: 241

Text #17

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7316. Min Act: -0.0001

Data Index: 1473023 (Python Code)

Max Activating Token Index: 511

Text #18

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6702. Min Act: -0.0001

Data Index: 1558847 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1405185 (Python Code)

Max Activating Token Index: 960