Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4068 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.2052. Min Act: -0.0001

Data Index: 1565727 (Python Code)

Max Activating Token Index: 244

Text #1

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1519699 (Python Code)

Max Activating Token Index: 145

Text #2

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1963. Min Act: -0.0001

Data Index: 856658 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1896. Min Act: -0.0001

Data Index: 1468915 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.2043. Min Act: -0.0001

Data Index: 1612782 (Python Code)

Max Activating Token Index: 800

Text #5

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1858. Min Act: -0.0001

Data Index: 930172 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1797. Min Act: -0.0001

Data Index: 1111724 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1518483 (Python Code)

Max Activating Token Index: 186

Text #8

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1628685 (Python Code)

Max Activating Token Index: 741

Text #9

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1504636 (Python Code)

Max Activating Token Index: 848

Text #10

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1684. Min Act: -0.0001

Data Index: 1522140 (Python Code)

Max Activating Token Index: 444

Text #11

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1549910 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1629044 (Python Code)

Max Activating Token Index: 712

Text #13

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1534531 (Python Code)

Max Activating Token Index: 720

Text #14

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1374534 (Python Code)

Max Activating Token Index: 118

Text #15

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1593. Min Act: -0.0001

Data Index: 1605537 (Python Code)

Max Activating Token Index: 360

Text #16

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1540. Min Act: -0.0001

Data Index: 1368986 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1513962 (Python Code)

Max Activating Token Index: 648

Text #18

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1655539 (Python Code)

Max Activating Token Index: 370

Text #19

Max Range: 0.2132. Min Range: -0.2132

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1511274 (Python Code)

Max Activating Token Index: 165