Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4417 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1045654 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1289. Min Act: -0.0000

Data Index: 832452 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1125. Min Act: -0.0000

Data Index: 639389 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1118. Min Act: 0.0000

Data Index: 783801 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1142. Min Act: -0.0000

Data Index: 79355 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1318678 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1094. Min Act: 0.0000

Data Index: 755714 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1252359 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1086. Min Act: 0.0000

Data Index: 202058 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1077. Min Act: -0.0000

Data Index: 642792 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1056. Min Act: 0.0000

Data Index: 26958 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1034. Min Act: -0.0000

Data Index: 716645 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1033. Min Act: -0.0000

Data Index: 1147844 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1017. Min Act: -0.0000

Data Index: 21618 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1260500 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0958. Min Act: 0.0000

Data Index: 339326 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0997. Min Act: -0.0000

Data Index: 879042 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0996. Min Act: 0.0000

Data Index: 404833 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0996. Min Act: 0.0000

Data Index: 1025516 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.0985. Min Act: -0.0000

Data Index: 970359 (C4 (Web Text))

Max Activating Token Index: 804