Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.2032. Min Act: -0.0001

Data Index: 135036 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1803. Min Act: -0.0000

Data Index: 237923 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1699. Min Act: 0.0004

Data Index: 898535 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1691. Min Act: 0.0003

Data Index: 388595 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1679. Min Act: 0.0001

Data Index: 434818 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1617. Min Act: 0.0000

Data Index: 325529 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1609. Min Act: 0.0000

Data Index: 339874 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1571. Min Act: -0.0000

Data Index: 153673 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1549. Min Act: 0.0002

Data Index: 195626 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1485. Min Act: 0.0001

Data Index: 570438 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1526. Min Act: 0.0000

Data Index: 113981 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1521. Min Act: -0.0000

Data Index: 317374 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1473. Min Act: 0.0002

Data Index: 512200 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1469. Min Act: 0.0004

Data Index: 986112 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1457. Min Act: -0.0000

Data Index: 756812 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1545. Min Act: 0.0001

Data Index: 333298 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1482. Min Act: -0.0000

Data Index: 347694 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1424. Min Act: 0.0000

Data Index: 1099446 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1436. Min Act: -0.0001

Data Index: 959423 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1474. Min Act: 0.0005

Data Index: 1342570 (C4 (Web Text))

Max Activating Token Index: 17