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

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

Neuron 1912 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: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0005

Data Index: 92070 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1620595 (Python Code)

Max Activating Token Index: 984

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1646765 (Python Code)

Max Activating Token Index: 138

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1128507 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0068. Min Act: -0.0005

Data Index: 596074 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0005

Data Index: 448236 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0006

Data Index: 996270 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0005

Data Index: 1512234 (Python Code)

Max Activating Token Index: 337

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0066. Min Act: -0.0006

Data Index: 354587 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1371540 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0005

Data Index: 311652 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0064. Min Act: -0.0005

Data Index: 188960 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1649131 (Python Code)

Max Activating Token Index: 992

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0005

Data Index: 1505598 (Python Code)

Max Activating Token Index: 573

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1616059 (Python Code)

Max Activating Token Index: 794

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0005

Data Index: 309177 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1431010 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0006

Data Index: 285750 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0005

Data Index: 1576741 (Python Code)

Max Activating Token Index: 697

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0006

Data Index: 655011 (C4 (Web Text))

Max Activating Token Index: 884