Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5024 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1009635 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1313252 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.7175. Min Act: -0.0000

Data Index: 306651 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6902. Min Act: -0.0000

Data Index: 1213925 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6664. Min Act: -0.0000

Data Index: 93864 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6788. Min Act: -0.0000

Data Index: 839095 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6324. Min Act: -0.0000

Data Index: 729575 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6898. Min Act: -0.0001

Data Index: 92864 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6632. Min Act: -0.0000

Data Index: 689656 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1083400 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1086684 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1154134 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1315564 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6057. Min Act: -0.0001

Data Index: 828853 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6097. Min Act: -0.0000

Data Index: 983793 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6083. Min Act: -0.0000

Data Index: 515488 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5835. Min Act: -0.0000

Data Index: 213226 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.5836. Min Act: -0.0000

Data Index: 39424 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6201. Min Act: -0.0000

Data Index: 166217 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.8073. Min Range: -0.8073

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1209984 (C4 (Web Text))

Max Activating Token Index: 682