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

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

Neuron 5041 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.7519. Min Act: -0.0000

Data Index: 396234 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.7173. Min Act: -0.0000

Data Index: 255200 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.2178. Min Act: -0.0000

Data Index: 955003 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.2458. Min Act: -0.0000

Data Index: 1271863 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.1956. Min Act: -0.0000

Data Index: 703229 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.1791. Min Act: -0.0000

Data Index: 1295068 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1141873 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.1990. Min Act: -0.0000

Data Index: 1083836 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.1058. Min Act: -0.0000

Data Index: 293368 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1139376 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.2889. Min Act: -0.0000

Data Index: 371949 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.1047. Min Act: -0.0000

Data Index: 1303397 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 1.7519. Min Range: -1.7519

Max Act: 0.8720. Min Act: -0.0000

Data Index: 590110 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 1.7519. Min Range: -1.7519

Max Act: 0.9223. Min Act: -0.0000

Data Index: 153396 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.0148. Min Act: -0.0000

Data Index: 1261274 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 1.7519. Min Range: -1.7519

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1081481 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.0075. Min Act: -0.0000

Data Index: 438066 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 1.7519. Min Range: -1.7519

Max Act: 0.9541. Min Act: -0.0000

Data Index: 603034 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 1.7519. Min Range: -1.7519

Max Act: 0.9374. Min Act: -0.0000

Data Index: 190426 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.7519. Min Range: -1.7519

Max Act: 1.0290. Min Act: -0.0000

Data Index: 39203 (C4 (Web Text))

Max Activating Token Index: 143