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

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

Neuron 3490 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1524. Min Act: -0.0001

Data Index: 498824 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1206. Min Act: -0.0001

Data Index: 415333 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1236. Min Act: -0.0001

Data Index: 485670 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1112. Min Act: -0.0001

Data Index: 159570 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1080. Min Act: -0.0001

Data Index: 649746 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1181. Min Act: -0.0001

Data Index: 974950 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1047. Min Act: -0.0001

Data Index: 713430 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1091. Min Act: -0.0001

Data Index: 925054 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1294182 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1201275 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1108. Min Act: -0.0001

Data Index: 642095 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1055. Min Act: -0.0001

Data Index: 307738 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0996. Min Act: -0.0001

Data Index: 114787 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1046. Min Act: -0.0001

Data Index: 112534 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1002. Min Act: -0.0001

Data Index: 345978 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1025. Min Act: -0.0001

Data Index: 261960 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0986. Min Act: -0.0001

Data Index: 234702 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0959. Min Act: -0.0001

Data Index: 709140 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1207474 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1235766 (C4 (Web Text))

Max Activating Token Index: 986