Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 28 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0093. Min Act: -0.0004

Data Index: 86372 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0081. Min Act: -0.0004

Data Index: 1210201 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0075. Min Act: -0.0004

Data Index: 518910 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0004

Data Index: 39839 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0004

Data Index: 457206 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0072. Min Act: -0.0004

Data Index: 564431 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0004

Data Index: 1143287 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0071. Min Act: -0.0004

Data Index: 155733 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0071. Min Act: -0.0004

Data Index: 813063 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0070. Min Act: -0.0004

Data Index: 313129 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0069. Min Act: -0.0004

Data Index: 911774 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0069. Min Act: -0.0004

Data Index: 301725 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0069. Min Act: -0.0004

Data Index: 874900 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0068. Min Act: -0.0004

Data Index: 826883 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0069. Min Act: -0.0004

Data Index: 883279 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1171168 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0068. Min Act: -0.0004

Data Index: 166939 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1422040 (Python Code)

Max Activating Token Index: 861

Text #18

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0067. Min Act: -0.0004

Data Index: 820195 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0067. Min Act: -0.0004

Data Index: 9892 (C4 (Web Text))

Max Activating Token Index: 814