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

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

Neuron 4908 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: 0.7969. Min Range: -0.7969

Max Act: 0.7969. Min Act: -0.0000

Data Index: 116080 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.7184. Min Act: -0.0001

Data Index: 1257553 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1255063 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6679. Min Act: -0.0000

Data Index: 175843 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.7013. Min Act: -0.0000

Data Index: 862259 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1337865 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.7367. Min Act: -0.0000

Data Index: 555596 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1275801 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1116758 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6516. Min Act: -0.0001

Data Index: 1025273 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5780. Min Act: -0.0000

Data Index: 991258 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1086897 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6301. Min Act: -0.0000

Data Index: 136568 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1173948 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5852. Min Act: -0.0000

Data Index: 807365 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6676. Min Act: -0.0000

Data Index: 990645 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6024. Min Act: -0.0001

Data Index: 551270 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.6150. Min Act: -0.0001

Data Index: 871925 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5956. Min Act: -0.0000

Data Index: 696448 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.7969. Min Range: -0.7969

Max Act: 0.5844. Min Act: -0.0000

Data Index: 581731 (C4 (Web Text))

Max Activating Token Index: 564