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

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

Neuron 2790 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0151. Min Range: -1.0151

Max Act: 1.0151. Min Act: -0.0001

Data Index: 1505333 (Python Code)

Max Activating Token Index: 683

Text #1

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7603. Min Act: -0.0001

Data Index: 1617098 (Python Code)

Max Activating Token Index: 840

Text #2

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7126. Min Act: -0.0001

Data Index: 1594459 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6830. Min Act: -0.0001

Data Index: 1549398 (Python Code)

Max Activating Token Index: 976

Text #4

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1586016 (Python Code)

Max Activating Token Index: 721

Text #5

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1517029 (Python Code)

Max Activating Token Index: 374

Text #6

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6859. Min Act: -0.0001

Data Index: 1409603 (Python Code)

Max Activating Token Index: 651

Text #7

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6768. Min Act: -0.0001

Data Index: 1614659 (Python Code)

Max Activating Token Index: 450

Text #8

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6681. Min Act: -0.0001

Data Index: 1612989 (Python Code)

Max Activating Token Index: 520

Text #9

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6736. Min Act: -0.0001

Data Index: 1557932 (Python Code)

Max Activating Token Index: 782

Text #10

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1629202 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7046. Min Act: -0.0001

Data Index: 1427546 (Python Code)

Max Activating Token Index: 854

Text #12

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6585. Min Act: -0.0001

Data Index: 1505825 (Python Code)

Max Activating Token Index: 801

Text #13

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6111. Min Act: -0.0001

Data Index: 1459428 (Python Code)

Max Activating Token Index: 470

Text #14

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6063. Min Act: -0.0001

Data Index: 1401739 (Python Code)

Max Activating Token Index: 1022

Text #15

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6498. Min Act: -0.0001

Data Index: 1486213 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6232. Min Act: -0.0001

Data Index: 1390484 (Python Code)

Max Activating Token Index: 476

Text #17

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.5861. Min Act: -0.0001

Data Index: 1526010 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6208. Min Act: -0.0001

Data Index: 1487621 (Python Code)

Max Activating Token Index: 741

Text #19

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.6155. Min Act: -0.0001

Data Index: 1456636 (Python Code)

Max Activating Token Index: 468