Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1893 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.5335. Min Act: -0.0000

Data Index: 39662 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.5908. Min Act: -0.0000

Data Index: 11558 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.5676. Min Act: -0.0000

Data Index: 952906 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.3257. Min Act: -0.0000

Data Index: 1161681 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.3245. Min Act: -0.0000

Data Index: 991244 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.3244. Min Act: -0.0000

Data Index: 320182 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.3033. Min Act: -0.0000

Data Index: 981921 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.3096. Min Act: -0.0000

Data Index: 401319 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.3438. Min Act: -0.0000

Data Index: 1348797 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.1983. Min Act: -0.0000

Data Index: 1289377 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.1831. Min Act: -0.0000

Data Index: 1117504 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.1546. Min Act: -0.0000

Data Index: 932651 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 2.5908. Min Range: -2.5908

Max Act: 1.8741. Min Act: -0.0000

Data Index: 126026 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.0553. Min Act: -0.0000

Data Index: 567750 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.0543. Min Act: -0.0000

Data Index: 603513 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.1530. Min Act: -0.0000

Data Index: 1093755 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.0926. Min Act: -0.0000

Data Index: 610258 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 2.5908. Min Range: -2.5908

Max Act: 1.8520. Min Act: -0.0000

Data Index: 1261589 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 2.5908. Min Range: -2.5908

Max Act: 1.8520. Min Act: -0.0000

Data Index: 815805 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 2.5908. Min Range: -2.5908

Max Act: 2.1441. Min Act: -0.0000

Data Index: 822061 (C4 (Web Text))

Max Activating Token Index: 378