Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 129 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0006

Data Index: 1414854 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0062. Min Act: -0.0006

Data Index: 293937 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1551220 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0005

Data Index: 1430689 (Python Code)

Max Activating Token Index: 493

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0060. Min Act: -0.0005

Data Index: 1482832 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0005

Data Index: 1474570 (Python Code)

Max Activating Token Index: 504

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1403967 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1210575 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1381704 (Python Code)

Max Activating Token Index: 1000

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1404284 (Python Code)

Max Activating Token Index: 217

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1403971 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0006

Data Index: 584740 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1431101 (Python Code)

Max Activating Token Index: 194

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1530347 (Python Code)

Max Activating Token Index: 1015

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0006

Data Index: 163278 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0006

Data Index: 860017 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1542035 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1574679 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0006

Data Index: 1376107 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0006

Data Index: 607259 (C4 (Web Text))

Max Activating Token Index: 916