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

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

Neuron 2181 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.1031. Min Act: -0.0002

Data Index: 505507 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0990. Min Act: -0.0002

Data Index: 464694 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0967. Min Act: -0.0002

Data Index: 808141 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0937. Min Act: -0.0002

Data Index: 260199 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0986. Min Act: -0.0002

Data Index: 270845 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1286175 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0935. Min Act: -0.0002

Data Index: 730500 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1012944 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1292370 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1053550 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0895. Min Act: -0.0002

Data Index: 768034 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1091769 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1171202 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0833. Min Act: -0.0002

Data Index: 844207 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1212835 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0862. Min Act: -0.0002

Data Index: 1314578 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0860. Min Act: -0.0002

Data Index: 759939 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0796. Min Act: -0.0002

Data Index: 699176 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0835. Min Act: -0.0002

Data Index: 660475 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.1031. Min Range: -0.1031

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1293370 (C4 (Web Text))

Max Activating Token Index: 82