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

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

Neuron 2460 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: 0.0076. Min Range: -0.0076

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1208155 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0073. Min Act: -0.0003

Data Index: 470154 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0062. Min Act: -0.0003

Data Index: 25329 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0003

Data Index: 328734 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0066. Min Act: -0.0003

Data Index: 226358 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0003

Data Index: 736980 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0072. Min Act: -0.0003

Data Index: 421856 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0063. Min Act: -0.0003

Data Index: 429051 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0064. Min Act: -0.0003

Data Index: 886285 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0061. Min Act: -0.0003

Data Index: 296071 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0049. Min Act: -0.0004

Data Index: 961826 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0004

Data Index: 569593 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0060. Min Act: -0.0003

Data Index: 492069 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1067600 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0063. Min Act: -0.0003

Data Index: 807917 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1221546 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0059. Min Act: -0.0003

Data Index: 567991 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1125551 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0066. Min Act: -0.0003

Data Index: 490514 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0063. Min Act: -0.0003

Data Index: 698328 (C4 (Web Text))

Max Activating Token Index: 10