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

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

Neuron 3828 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: 0.0086. Min Range: -0.0086

Max Act: 0.0085. Min Act: -0.0003

Data Index: 608446 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1299844 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0082. Min Act: -0.0003

Data Index: 711415 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0077. Min Act: -0.0003

Data Index: 218913 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1311152 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0073. Min Act: -0.0003

Data Index: 163740 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1176218 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0066. Min Act: -0.0003

Data Index: 350736 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1174503 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0003

Data Index: 260550 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1378142 (Python Code)

Max Activating Token Index: 727

Text #12

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1282141 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1029056 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0066. Min Act: -0.0003

Data Index: 626662 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0067. Min Act: -0.0003

Data Index: 95884 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1214992 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0077. Min Act: -0.0003

Data Index: 133031 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0064. Min Act: -0.0003

Data Index: 654716 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0068. Min Act: -0.0003

Data Index: 293195 (C4 (Web Text))

Max Activating Token Index: 834