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

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

Neuron 4777 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7989. Min Range: -6.7989

Max Act: 6.7989. Min Act: -0.0000

Data Index: 56617 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 6.7989. Min Range: -6.7989

Max Act: 6.4887. Min Act: -0.0000

Data Index: 1502560 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 6.7989. Min Range: -6.7989

Max Act: 6.2781. Min Act: -0.0000

Data Index: 164811 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.9454. Min Act: -0.0000

Data Index: 693077 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.6439. Min Act: -0.0000

Data Index: 1011995 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.5643. Min Act: -0.0000

Data Index: 510008 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.5045. Min Act: -0.0000

Data Index: 548628 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.2990. Min Act: -0.0000

Data Index: 933943 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.6220. Min Act: -0.0000

Data Index: 677343 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.3797. Min Act: -0.0000

Data Index: 877609 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.0986. Min Act: -0.0000

Data Index: 943669 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.0286. Min Act: -0.0000

Data Index: 819469 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 6.7989. Min Range: -6.7989

Max Act: 4.9750. Min Act: -0.0000

Data Index: 67850 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 6.7989. Min Range: -6.7989

Max Act: 5.1173. Min Act: -0.0000

Data Index: 941596 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 6.7989. Min Range: -6.7989

Max Act: 4.5326. Min Act: -0.0000

Data Index: 1113100 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 6.7989. Min Range: -6.7989

Max Act: 4.6840. Min Act: -0.0000

Data Index: 757703 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 6.7989. Min Range: -6.7989

Max Act: 4.3211. Min Act: -0.0000

Data Index: 7077 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 6.7989. Min Range: -6.7989

Max Act: 4.3385. Min Act: -0.0000

Data Index: 839884 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 6.7989. Min Range: -6.7989

Max Act: 4.3181. Min Act: -0.0000

Data Index: 337405 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 6.7989. Min Range: -6.7989

Max Act: 3.9156. Min Act: -0.0000

Data Index: 1104059 (C4 (Web Text))

Max Activating Token Index: 246