Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1753 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1842. Min Act: -0.0001

Data Index: 220314 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1580. Min Act: -0.0001

Data Index: 403447 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1004. Min Act: -0.0000

Data Index: 931273 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1133. Min Act: -0.0001

Data Index: 1175434 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1134. Min Act: -0.0001

Data Index: 580681 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1055. Min Act: -0.0001

Data Index: 979895 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1044. Min Act: -0.0001

Data Index: 729151 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1288867 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1037. Min Act: -0.0001

Data Index: 851771 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0998. Min Act: -0.0001

Data Index: 639235 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1030. Min Act: -0.0001

Data Index: 780788 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0980. Min Act: -0.0001

Data Index: 900528 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1058. Min Act: -0.0001

Data Index: 411167 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1544225 (Python Code)

Max Activating Token Index: 483

Text #14

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1053259 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0963. Min Act: -0.0001

Data Index: 103254 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1002. Min Act: -0.0001

Data Index: 298343 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1435711 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1557837 (Python Code)

Max Activating Token Index: 528

Text #19

Max Range: 0.1842. Min Range: -0.1842

Max Act: 0.1010. Min Act: -0.0001

Data Index: 955883 (C4 (Web Text))

Max Activating Token Index: 284