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

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

Neuron 6046 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.2221. Min Act: -0.0000

Data Index: 171859 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.1443. Min Act: -0.0000

Data Index: 651176 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.1017. Min Act: -0.0000

Data Index: 287882 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.0262. Min Act: -0.0000

Data Index: 714686 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.2221. Min Range: -1.2221

Max Act: 1.0889. Min Act: -0.0000

Data Index: 339285 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9162. Min Act: -0.0000

Data Index: 837125 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9088. Min Act: -0.0000

Data Index: 607886 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9524. Min Act: -0.0000

Data Index: 878653 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8858. Min Act: -0.0000

Data Index: 838003 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8851. Min Act: -0.0000

Data Index: 421248 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1332960 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8310. Min Act: -0.0000

Data Index: 738166 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8890. Min Act: -0.0000

Data Index: 327369 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8268. Min Act: -0.0000

Data Index: 933376 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8238. Min Act: -0.0000

Data Index: 305348 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7724. Min Act: -0.0000

Data Index: 713689 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8159. Min Act: -0.0000

Data Index: 921131 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.8625. Min Act: -0.0000

Data Index: 871434 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7899. Min Act: -0.0000

Data Index: 445719 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 1.2221. Min Range: -1.2221

Max Act: 0.7419. Min Act: -0.0000

Data Index: 407233 (C4 (Web Text))

Max Activating Token Index: 144