Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2214 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1152. Min Act: -0.0001

Data Index: 253352 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1087. Min Act: -0.0001

Data Index: 526838 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1358003 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1216. Min Act: -0.0001

Data Index: 255406 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1096. Min Act: -0.0001

Data Index: 549422 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1092. Min Act: -0.0001

Data Index: 695725 (C4 (Web Text))

Max Activating Token Index: 211

Text #6

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1147. Min Act: -0.0001

Data Index: 806983 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1093. Min Act: -0.0001

Data Index: 375410 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1062. Min Act: -0.0001

Data Index: 699895 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1154. Min Act: -0.0001

Data Index: 919358 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1110. Min Act: -0.0001

Data Index: 770883 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1277589 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1069. Min Act: -0.0001

Data Index: 52298 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1101. Min Act: -0.0001

Data Index: 89788 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1085. Min Act: -0.0001

Data Index: 746384 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1060. Min Act: -0.0001

Data Index: 180739 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0980. Min Act: -0.0001

Data Index: 749755 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1572900 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1294378 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1007. Min Act: -0.0001

Data Index: 465181 (C4 (Web Text))

Max Activating Token Index: 472