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

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

Neuron 1314 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1495. Min Act: -0.0001

Data Index: 918347 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1026000 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1001567 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1247. Min Act: -0.0001

Data Index: 869873 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1242. Min Act: -0.0001

Data Index: 576380 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1122. Min Act: -0.0001

Data Index: 169404 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1163. Min Act: -0.0001

Data Index: 109157 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1281. Min Act: -0.0001

Data Index: 990028 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1245. Min Act: -0.0001

Data Index: 175742 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1152. Min Act: -0.0001

Data Index: 671733 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1223. Min Act: -0.0000

Data Index: 112241 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1057. Min Act: -0.0001

Data Index: 509771 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1075. Min Act: -0.0001

Data Index: 994756 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1069. Min Act: -0.0001

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1033. Min Act: -0.0001

Data Index: 286808 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1093. Min Act: -0.0001

Data Index: 599493 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1095895 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0972. Min Act: -0.0001

Data Index: 386946 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1050. Min Act: -0.0001

Data Index: 756056 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0996. Min Act: -0.0001

Data Index: 735639 (C4 (Web Text))

Max Activating Token Index: 51