Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2465 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0114. Min Act: -0.0003

Data Index: 340151 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1186082 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0096. Min Act: -0.0003

Data Index: 1155708 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0093. Min Act: -0.0003

Data Index: 890912 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1045000 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1200237 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0080. Min Act: -0.0003

Data Index: 1331728 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0074. Min Act: -0.0003

Data Index: 4947 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0075. Min Act: -0.0003

Data Index: 335905 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0077. Min Act: -0.0003

Data Index: 771178 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0077. Min Act: -0.0003

Data Index: 494503 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0074. Min Act: -0.0003

Data Index: 4917 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0074. Min Act: -0.0003

Data Index: 594716 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0073. Min Act: -0.0003

Data Index: 351792 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0072. Min Act: -0.0003

Data Index: 637947 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1407995 (Python Code)

Max Activating Token Index: 870

Text #16

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0075. Min Act: -0.0003

Data Index: 603478 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1486130 (Python Code)

Max Activating Token Index: 617

Text #18

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0069. Min Act: -0.0003

Data Index: 257191 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1100477 (C4 (Web Text))

Max Activating Token Index: 98