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

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

Neuron 4010 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1374. Min Act: -0.0002

Data Index: 1077895 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1307. Min Act: -0.0002

Data Index: 331579 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1240. Min Act: -0.0002

Data Index: 306211 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1301712 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1180. Min Act: -0.0002

Data Index: 518809 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1215. Min Act: -0.0002

Data Index: 529330 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1197. Min Act: -0.0002

Data Index: 1176861 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1187. Min Act: -0.0002

Data Index: 574162 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1130. Min Act: -0.0002

Data Index: 195052 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1093. Min Act: -0.0002

Data Index: 594372 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1113. Min Act: -0.0002

Data Index: 533304 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1107. Min Act: -0.0002

Data Index: 433634 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1063. Min Act: -0.0002

Data Index: 147857 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1042. Min Act: -0.0002

Data Index: 207819 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.1049. Min Act: -0.0002

Data Index: 876798 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.0959. Min Act: -0.0002

Data Index: 584538 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.0903. Min Act: -0.0002

Data Index: 348341 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1022859 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1358683 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.1374. Min Range: -0.1374

Max Act: 0.0876. Min Act: -0.0002

Data Index: 496076 (C4 (Web Text))

Max Activating Token Index: 903