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

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

Neuron 2433 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.9141. Min Act: -0.0000

Data Index: 675689 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 2.1835. Min Range: -2.1835

Max Act: 2.1835. Min Act: -0.0000

Data Index: 939496 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 2.1835. Min Range: -2.1835

Max Act: 2.0157. Min Act: -0.0000

Data Index: 1082925 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.8320. Min Act: -0.0000

Data Index: 883038 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.7017. Min Act: -0.0000

Data Index: 224648 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.7063. Min Act: -0.0000

Data Index: 285964 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.3821. Min Act: -0.0000

Data Index: 994585 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1219453 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.3056. Min Act: -0.0000

Data Index: 152435 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.2098. Min Act: -0.0000

Data Index: 990640 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.1329. Min Act: -0.0000

Data Index: 230461 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.1252. Min Act: -0.0000

Data Index: 950288 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.2989. Min Act: -0.0000

Data Index: 65183 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.1439. Min Act: -0.0000

Data Index: 679932 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.1223. Min Act: -0.0000

Data Index: 402342 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.1852. Min Act: -0.0000

Data Index: 20121 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.0595. Min Act: -0.0000

Data Index: 498249 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.0354. Min Act: -0.0000

Data Index: 3652 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 2.1835. Min Range: -2.1835

Max Act: 0.9510. Min Act: -0.0000

Data Index: 830225 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 2.1835. Min Range: -2.1835

Max Act: 1.2245. Min Act: -0.0000

Data Index: 781515 (C4 (Web Text))

Max Activating Token Index: 793