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

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

Neuron 3739 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.5781. Min Act: -0.0000

Data Index: 60112 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.4472. Min Act: -0.0000

Data Index: 608404 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.4973. Min Act: -0.0000

Data Index: 346284 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.3525. Min Act: -0.0000

Data Index: 453666 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.3027. Min Act: -0.0000

Data Index: 975814 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.2351. Min Act: -0.0000

Data Index: 1019524 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1630946 (Python Code)

Max Activating Token Index: 909

Text #7

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.1480. Min Act: -0.0000

Data Index: 757123 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1219256 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.2281. Min Act: -0.0000

Data Index: 1310396 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.0759. Min Act: -0.0000

Data Index: 699086 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1634590 (Python Code)

Max Activating Token Index: 697

Text #12

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1080806 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.0749. Min Act: -0.0000

Data Index: 566637 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1204941 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.5781. Min Range: -1.5781

Max Act: 0.9908. Min Act: -0.0000

Data Index: 337128 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1561070 (Python Code)

Max Activating Token Index: 678

Text #17

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1111623 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.5781. Min Range: -1.5781

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1408180 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 1.5781. Min Range: -1.5781

Max Act: 1.0074. Min Act: -0.0000

Data Index: 97989 (C4 (Web Text))

Max Activating Token Index: 67