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

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

Neuron 4840 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: 2.8681. Min Range: -2.8681

Max Act: 2.8681. Min Act: -0.0000

Data Index: 446601 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.1266. Min Act: -0.0000

Data Index: 118300 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.0987. Min Act: -0.0000

Data Index: 536079 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.0931. Min Act: -0.0000

Data Index: 1567309 (Python Code)

Max Activating Token Index: 745

Text #4

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.0708. Min Act: -0.0000

Data Index: 1014066 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.8856. Min Act: -0.0000

Data Index: 935979 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 2.8681. Min Range: -2.8681

Max Act: 2.0064. Min Act: -0.0000

Data Index: 1241890 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.8765. Min Act: -0.0000

Data Index: 1537821 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.7552. Min Act: -0.0000

Data Index: 1338570 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.8470. Min Act: -0.0000

Data Index: 356245 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.8003. Min Act: -0.0000

Data Index: 517356 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.7992. Min Act: -0.0000

Data Index: 22173 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.7784. Min Act: -0.0000

Data Index: 444017 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.7481. Min Act: -0.0000

Data Index: 1249192 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.8197. Min Act: -0.0000

Data Index: 630004 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.7105. Min Act: -0.0000

Data Index: 766888 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1014191 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.7061. Min Act: -0.0000

Data Index: 867291 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.7975. Min Act: -0.0000

Data Index: 1109611 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 2.8681. Min Range: -2.8681

Max Act: 1.6805. Min Act: -0.0000

Data Index: 1087860 (C4 (Web Text))

Max Activating Token Index: 637