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

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

Neuron 1638 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 106692 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 37017 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 137635 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1338081 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1310279 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1072203 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 412680 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 95039 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1206380 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 377434 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 592603 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1246553 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 595248 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 13650 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 935179 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 525818 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 833919 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 810839 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 554483 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.0002. Min Range: -0.0002

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1098421 (C4 (Web Text))

Max Activating Token Index: 838