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

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

Neuron 3362 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.4235. Min Act: -0.0001

Data Index: 1163505 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.2981. Min Act: -0.0001

Data Index: 624715 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.5094. Min Act: -0.0001

Data Index: 183788 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.5014. Min Act: -0.0000

Data Index: 845708 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.3471. Min Act: -0.0000

Data Index: 126746 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.4960. Min Act: -0.0001

Data Index: 202834 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.2574. Min Act: -0.0000

Data Index: 1022446 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.2254. Min Act: -0.0001

Data Index: 157517 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.3271. Min Act: -0.0000

Data Index: 874350 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.1264. Min Act: -0.0000

Data Index: 840159 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.2101. Min Act: -0.0000

Data Index: 700402 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 2.5094. Min Range: -2.5094

Max Act: 1.9730. Min Act: -0.0000

Data Index: 167987 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.1729. Min Act: -0.0000

Data Index: 675547 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.1122. Min Act: -0.0001

Data Index: 784115 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.2168. Min Act: -0.0001

Data Index: 643509 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.2291. Min Act: -0.0001

Data Index: 664992 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.0614. Min Act: -0.0000

Data Index: 432010 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.0210. Min Act: -0.0000

Data Index: 1188007 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 2.5094. Min Range: -2.5094

Max Act: 2.0516. Min Act: -0.0001

Data Index: 437877 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 2.5094. Min Range: -2.5094

Max Act: 1.5473. Min Act: -0.0000

Data Index: 1227195 (C4 (Web Text))

Max Activating Token Index: 20