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

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

Neuron 517 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.9078. Min Act: -0.0003

Data Index: 901920 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.8789. Min Act: -0.0003

Data Index: 515471 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.7795. Min Act: -0.0003

Data Index: 565265 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6871. Min Act: -0.0003

Data Index: 1203316 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.7860. Min Act: -0.0003

Data Index: 1244816 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.7138. Min Act: -0.0003

Data Index: 1187149 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.7924. Min Act: -0.0003

Data Index: 1192829 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.7080. Min Act: -0.0003

Data Index: 1067999 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6896. Min Act: -0.0003

Data Index: 427299 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6683. Min Act: -0.0003

Data Index: 153419 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6848. Min Act: -0.0003

Data Index: 763306 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6346. Min Act: -0.0003

Data Index: 709371 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6792. Min Act: -0.0003

Data Index: 551492 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6732. Min Act: -0.0003

Data Index: 1176531 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6684. Min Act: -0.0003

Data Index: 982662 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6331. Min Act: -0.0003

Data Index: 473991 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6526. Min Act: -0.0003

Data Index: 1351380 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6650. Min Act: -0.0003

Data Index: 1354256 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.5481. Min Act: -0.0003

Data Index: 956345 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6150. Min Act: -0.0003

Data Index: 381430 (C4 (Web Text))

Max Activating Token Index: 229