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

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

Neuron 5075 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1270. Min Act: -0.0000

Data Index: 479715 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1095. Min Act: -0.0000

Data Index: 139608 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1065166 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1100. Min Act: -0.0000

Data Index: 348754 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1075. Min Act: -0.0000

Data Index: 399597 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1034. Min Act: -0.0000

Data Index: 356703 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1023. Min Act: -0.0000

Data Index: 210432 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1025. Min Act: -0.0000

Data Index: 794868 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1057439 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0999. Min Act: -0.0000

Data Index: 533654 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0948. Min Act: -0.0000

Data Index: 854950 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0974. Min Act: -0.0000

Data Index: 886709 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1265223 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1199409 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0963. Min Act: -0.0000

Data Index: 550085 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0953. Min Act: -0.0000

Data Index: 183741 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0949. Min Act: -0.0000

Data Index: 561594 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0947. Min Act: -0.0000

Data Index: 438233 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0972. Min Act: -0.0000

Data Index: 349266 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.1270. Min Range: -0.1270

Max Act: 0.0904. Min Act: -0.0000

Data Index: 265372 (C4 (Web Text))

Max Activating Token Index: 770