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

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

Neuron 5039 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1519863 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1514712 (Python Code)

Max Activating Token Index: 558

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1526614 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1510373 (Python Code)

Max Activating Token Index: 458

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1630751 (Python Code)

Max Activating Token Index: 723

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1390243 (Python Code)

Max Activating Token Index: 644

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1369440 (Python Code)

Max Activating Token Index: 963

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1470807 (Python Code)

Max Activating Token Index: 872

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1411270 (Python Code)

Max Activating Token Index: 903

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1628658 (Python Code)

Max Activating Token Index: 950

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1522047 (Python Code)

Max Activating Token Index: 125

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1507806 (Python Code)

Max Activating Token Index: 1011

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1515689 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1536685 (Python Code)

Max Activating Token Index: 120

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1469021 (Python Code)

Max Activating Token Index: 228

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1555262 (Python Code)

Max Activating Token Index: 832

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1443778 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1464376 (Python Code)

Max Activating Token Index: 282

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1518012 (Python Code)

Max Activating Token Index: 244

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1535250 (Python Code)

Max Activating Token Index: 959