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

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

Neuron 479 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1240815 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1040. Min Act: -0.0000

Data Index: 982606 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1062. Min Act: -0.0000

Data Index: 207779 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1235058 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1271082 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0920. Min Act: -0.0000

Data Index: 22782 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0902. Min Act: -0.0000

Data Index: 936770 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0897. Min Act: -0.0000

Data Index: 908040 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1333262 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0832. Min Act: -0.0001

Data Index: 899149 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0884. Min Act: -0.0000

Data Index: 439978 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1310525 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1177723 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0841. Min Act: -0.0000

Data Index: 854335 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0856. Min Act: -0.0000

Data Index: 4394 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0762. Min Act: -0.0000

Data Index: 179713 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0784. Min Act: -0.0000

Data Index: 916552 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1010387 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0890. Min Act: -0.0000

Data Index: 719772 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0797. Min Act: -0.0000

Data Index: 934537 (C4 (Web Text))

Max Activating Token Index: 396