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

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

Neuron 1409 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: 2.6891. Min Range: -2.6891

Max Act: 2.6891. Min Act: -0.0000

Data Index: 613150 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 2.6891. Min Range: -2.6891

Max Act: 2.2019. Min Act: -0.0000

Data Index: 146059 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 2.6891. Min Range: -2.6891

Max Act: 2.1727. Min Act: -0.0000

Data Index: 238415 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 2.6891. Min Range: -2.6891

Max Act: 2.2092. Min Act: -0.0000

Data Index: 1092641 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 2.6891. Min Range: -2.6891

Max Act: 2.0907. Min Act: -0.0000

Data Index: 869563 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 2.6891. Min Range: -2.6891

Max Act: 2.2748. Min Act: -0.0000

Data Index: 965830 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 2.6891. Min Range: -2.6891

Max Act: 2.0539. Min Act: -0.0000

Data Index: 88298 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 2.6891. Min Range: -2.6891

Max Act: 2.0159. Min Act: -0.0000

Data Index: 925517 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 2.6891. Min Range: -2.6891

Max Act: 2.0197. Min Act: -0.0000

Data Index: 1179103 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.9979. Min Act: -0.0000

Data Index: 573107 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.7901. Min Act: -0.0000

Data Index: 247335 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.8902. Min Act: -0.0000

Data Index: 259765 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.8426. Min Act: -0.0000

Data Index: 375100 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.8002. Min Act: -0.0000

Data Index: 21005 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.7781. Min Act: -0.0000

Data Index: 500017 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.8944. Min Act: -0.0000

Data Index: 491492 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.7173. Min Act: -0.0000

Data Index: 1104991 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.7018. Min Act: -0.0000

Data Index: 1349244 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.7044. Min Act: -0.0000

Data Index: 818158 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 2.6891. Min Range: -2.6891

Max Act: 1.7051. Min Act: -0.0000

Data Index: 951831 (C4 (Web Text))

Max Activating Token Index: 348