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

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

Neuron 4246 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.9767. Min Act: -0.0000

Data Index: 1189875 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 3.0669. Min Range: -3.0669

Max Act: 3.0669. Min Act: -0.0000

Data Index: 1251318 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.7692. Min Act: -0.0000

Data Index: 604009 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.9614. Min Act: -0.0000

Data Index: 1048570 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.9380. Min Act: -0.0000

Data Index: 602778 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.8008. Min Act: -0.0000

Data Index: 1067315 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.8732. Min Act: -0.0000

Data Index: 204441 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.8477. Min Act: -0.0000

Data Index: 1041913 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.5650. Min Act: -0.0000

Data Index: 1023613 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.6336. Min Act: 0.0002

Data Index: 203208 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.6322. Min Act: -0.0000

Data Index: 1100432 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.6116. Min Act: -0.0000

Data Index: 160335 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.7240. Min Act: -0.0000

Data Index: 527648 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.5773. Min Act: -0.0000

Data Index: 504961 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.5571. Min Act: -0.0000

Data Index: 1285397 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.4574. Min Act: -0.0000

Data Index: 1074186 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.5369. Min Act: -0.0000

Data Index: 309536 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.5213. Min Act: -0.0000

Data Index: 285991 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.5134. Min Act: -0.0000

Data Index: 1032538 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 3.0669. Min Range: -3.0669

Max Act: 2.4918. Min Act: -0.0000

Data Index: 1062842 (C4 (Web Text))

Max Activating Token Index: 675