Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 350 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1822. Min Act: 0.0001

Data Index: 1002253 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1635. Min Act: 0.0000

Data Index: 288605 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1421. Min Act: -0.0001

Data Index: 508295 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1115. Min Act: 0.0000

Data Index: 970362 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1223. Min Act: -0.0001

Data Index: 422806 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1157. Min Act: -0.0001

Data Index: 9670 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1094. Min Act: 0.0000

Data Index: 95917 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1144. Min Act: 0.0000

Data Index: 1016073 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1060. Min Act: 0.0000

Data Index: 512569 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1080. Min Act: 0.0000

Data Index: 682997 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1068. Min Act: -0.0001

Data Index: 1065518 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1057. Min Act: -0.0001

Data Index: 730292 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1053. Min Act: -0.0000

Data Index: 488076 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1053. Min Act: -0.0000

Data Index: 204908 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1084. Min Act: 0.0000

Data Index: 796256 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1062. Min Act: -0.0001

Data Index: 367510 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1076. Min Act: 0.0000

Data Index: 692340 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1040. Min Act: -0.0000

Data Index: 61186 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.1109. Min Act: -0.0000

Data Index: 187976 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.1822. Min Range: -0.1822

Max Act: 0.0938. Min Act: 0.0000

Data Index: 633247 (C4 (Web Text))

Max Activating Token Index: 211