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

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

Neuron 1332 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1652. Min Act: -0.0002

Data Index: 674750 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1652. Min Act: -0.0003

Data Index: 1530819 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1652. Min Act: -0.0003

Data Index: 87354 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1652. Min Act: -0.0002

Data Index: 1173534 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1512. Min Act: -0.0002

Data Index: 1363499 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1512. Min Act: -0.0002

Data Index: 1424315 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1512. Min Act: -0.0002

Data Index: 1655525 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1512. Min Act: -0.0003

Data Index: 1638036 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0003

Data Index: 1406496 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0003

Data Index: 1547367 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0002

Data Index: 1546306 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0003

Data Index: 1384798 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0003

Data Index: 1450748 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0003

Data Index: 1411140 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0002

Data Index: 1459131 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0002

Data Index: 1393668 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0002

Data Index: 1494963 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0002

Data Index: 1394352 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0003

Data Index: 1376055 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.1652. Min Range: -0.1652

Max Act: 0.1491. Min Act: -0.0002

Data Index: 1428429 (Python Code)

Max Activating Token Index: 1