Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1479 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1150. Min Act: -0.0001

Data Index: 822707 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1145. Min Act: -0.0002

Data Index: 8235 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1174. Min Act: -0.0002

Data Index: 872508 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1132. Min Act: -0.0002

Data Index: 670435 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1155. Min Act: -0.0002

Data Index: 806377 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1079807 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1027217 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1110. Min Act: -0.0002

Data Index: 110422 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1060. Min Act: -0.0002

Data Index: 310663 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1061. Min Act: -0.0002

Data Index: 60169 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1043. Min Act: -0.0002

Data Index: 121186 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1048. Min Act: -0.0002

Data Index: 372779 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1002. Min Act: -0.0002

Data Index: 697757 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1182246 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1026. Min Act: -0.0002

Data Index: 577811 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1016. Min Act: -0.0002

Data Index: 509192 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1014. Min Act: -0.0002

Data Index: 542836 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1020. Min Act: -0.0002

Data Index: 984412 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1011. Min Act: -0.0002

Data Index: 458180 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.1174. Min Range: -0.1174

Max Act: 0.1005. Min Act: -0.0002

Data Index: 741518 (C4 (Web Text))

Max Activating Token Index: 25