Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4157 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1413993 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1731. Min Act: -0.0001

Data Index: 451779 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1736. Min Act: -0.0001

Data Index: 759261 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1740. Min Act: -0.0001

Data Index: 1574604 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1599630 (Python Code)

Max Activating Token Index: 16

Text #5

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1730. Min Act: -0.0001

Data Index: 428643 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1703. Min Act: -0.0001

Data Index: 706920 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1036546 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1667. Min Act: -0.0001

Data Index: 303045 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1221242 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1488643 (Python Code)

Max Activating Token Index: 80

Text #11

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1662. Min Act: -0.0001

Data Index: 656957 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1680. Min Act: -0.0001

Data Index: 666355 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1261062 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1120468 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1684. Min Act: -0.0001

Data Index: 1497516 (Python Code)

Max Activating Token Index: 649

Text #16

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1655. Min Act: -0.0001

Data Index: 1583342 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1273685 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1094731 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.1782. Min Range: -0.1782

Max Act: 0.1641. Min Act: -0.0001

Data Index: 979406 (C4 (Web Text))

Max Activating Token Index: 3