Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 71 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1470302 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1376798 (Python Code)

Max Activating Token Index: 379

Text #2

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0852. Min Act: -0.0002

Data Index: 684222 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0843. Min Act: -0.0002

Data Index: 457418 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1447140 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1622945 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1464288 (Python Code)

Max Activating Token Index: 336

Text #7

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1613199 (Python Code)

Max Activating Token Index: 608

Text #8

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1447461 (Python Code)

Max Activating Token Index: 64

Text #9

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1613739 (Python Code)

Max Activating Token Index: 318

Text #10

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1384102 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1382126 (Python Code)

Max Activating Token Index: 776

Text #12

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1599355 (Python Code)

Max Activating Token Index: 285

Text #13

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1585112 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1117575 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1649501 (Python Code)

Max Activating Token Index: 416

Text #16

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1436192 (Python Code)

Max Activating Token Index: 148

Text #17

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1374442 (Python Code)

Max Activating Token Index: 201

Text #18

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1402866 (Python Code)

Max Activating Token Index: 10

Text #19

Max Range: 0.0970. Min Range: -0.0970

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1623959 (Python Code)

Max Activating Token Index: 684