Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1527 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1251. Min Act: -0.0005

Data Index: 1347025 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1287. Min Act: -0.0005

Data Index: 254411 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1111. Min Act: -0.0005

Data Index: 1096099 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1041. Min Act: -0.0005

Data Index: 633803 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1028. Min Act: -0.0005

Data Index: 875167 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1027. Min Act: -0.0005

Data Index: 1030720 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0986. Min Act: -0.0005

Data Index: 166010 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1036. Min Act: -0.0005

Data Index: 557096 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1109. Min Act: -0.0005

Data Index: 204619 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1060. Min Act: -0.0005

Data Index: 692953 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1045. Min Act: -0.0005

Data Index: 1285384 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0996. Min Act: -0.0005

Data Index: 40727 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1107. Min Act: -0.0005

Data Index: 1083600 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1030. Min Act: -0.0005

Data Index: 657551 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1067. Min Act: -0.0005

Data Index: 631910 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1011. Min Act: -0.0005

Data Index: 66355 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0975. Min Act: -0.0005

Data Index: 1296175 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0906. Min Act: -0.0005

Data Index: 864037 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1023. Min Act: -0.0005

Data Index: 444832 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.0982. Min Act: -0.0005

Data Index: 451932 (C4 (Web Text))

Max Activating Token Index: 365