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

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

Neuron 50 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1137. Min Act: -0.0002

Data Index: 989435 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1130. Min Act: -0.0001

Data Index: 310104 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1312782 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1170720 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1157. Min Act: -0.0002

Data Index: 60402 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1090. Min Act: -0.0001

Data Index: 518785 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1035. Min Act: -0.0001

Data Index: 821280 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1091. Min Act: -0.0002

Data Index: 460623 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1108255 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1066. Min Act: -0.0001

Data Index: 798617 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1032. Min Act: -0.0002

Data Index: 311896 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1027. Min Act: -0.0001

Data Index: 543729 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1028. Min Act: -0.0002

Data Index: 387278 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1215007 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1032. Min Act: -0.0001

Data Index: 914442 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1005. Min Act: -0.0002

Data Index: 387754 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1018. Min Act: -0.0002

Data Index: 957922 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1187745 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1298127 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.1157. Min Range: -0.1157

Max Act: 0.0991. Min Act: -0.0002

Data Index: 566707 (C4 (Web Text))

Max Activating Token Index: 282