Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3406 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1105042 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1488. Min Act: -0.0000

Data Index: 582959 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1454. Min Act: 0.0000

Data Index: 275485 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1475. Min Act: -0.0000

Data Index: 482689 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1757 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1146. Min Act: -0.0000

Data Index: 971461 (C4 (Web Text))

Max Activating Token Index: 12

Text #6

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1083608 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1170. Min Act: -0.0000

Data Index: 193678 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1096. Min Act: -0.0000

Data Index: 752408 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1125. Min Act: -0.0000

Data Index: 151090 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1093. Min Act: -0.0000

Data Index: 522442 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1083. Min Act: -0.0000

Data Index: 937229 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1116. Min Act: -0.0000

Data Index: 711257 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1019. Min Act: -0.0000

Data Index: 811303 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1353322 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1031. Min Act: -0.0000

Data Index: 224442 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1019. Min Act: -0.0000

Data Index: 40864 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1053. Min Act: -0.0000

Data Index: 837740 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1073668 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.1876. Min Range: -0.1876

Max Act: 0.0989. Min Act: -0.0000

Data Index: 665167 (C4 (Web Text))

Max Activating Token Index: 784