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

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

Neuron 5181 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.8659. Min Act: -0.0001

Data Index: 177880 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1156205 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.7645. Min Act: -0.0001

Data Index: 1255629 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.7083. Min Act: -0.0001

Data Index: 1183977 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.7227. Min Act: -0.0000

Data Index: 77237 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6608. Min Act: -0.0001

Data Index: 1158395 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6118. Min Act: -0.0000

Data Index: 752588 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1197734 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6604. Min Act: -0.0001

Data Index: 145266 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1639021 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6428. Min Act: -0.0001

Data Index: 478573 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6357. Min Act: -0.0001

Data Index: 1292267 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6592. Min Act: -0.0001

Data Index: 764503 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6257. Min Act: -0.0001

Data Index: 146324 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.5878. Min Act: -0.0000

Data Index: 26467 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.5916. Min Act: -0.0000

Data Index: 801096 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6054. Min Act: -0.0000

Data Index: 846196 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.5959. Min Act: -0.0001

Data Index: 687998 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6164. Min Act: -0.0001

Data Index: 15723 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.8820. Min Range: -0.8820

Max Act: 0.6067. Min Act: -0.0001

Data Index: 339764 (C4 (Web Text))

Max Activating Token Index: 148