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

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

Neuron 2562 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.8837. Min Act: -0.0000

Data Index: 203015 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.6530. Min Act: -0.0000

Data Index: 1077702 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.5176. Min Act: -0.0000

Data Index: 906577 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.6106. Min Act: -0.0000

Data Index: 597129 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.5684. Min Act: -0.0000

Data Index: 570082 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.5036. Min Act: -0.0000

Data Index: 397884 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.4168. Min Act: -0.0000

Data Index: 910248 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.5746. Min Act: -0.0000

Data Index: 1149032 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.4950. Min Act: -0.0000

Data Index: 345385 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.4709. Min Act: -0.0000

Data Index: 1140472 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.5196. Min Act: -0.0000

Data Index: 246055 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.4263. Min Act: -0.0000

Data Index: 760105 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.4165. Min Act: -0.0000

Data Index: 173526 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.3343. Min Act: -0.0000

Data Index: 345730 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1351046 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.4946. Min Act: -0.0000

Data Index: 554103 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.3005. Min Act: -0.0000

Data Index: 1081648 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.3120. Min Act: -0.0000

Data Index: 238604 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.2894. Min Act: -0.0000

Data Index: 1347457 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 1.8837. Min Range: -1.8837

Max Act: 1.4571. Min Act: -0.0000

Data Index: 615476 (C4 (Web Text))

Max Activating Token Index: 32