Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 892 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1381455 (Python Code)

Max Activating Token Index: 328

Text #1

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1325232 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1619050 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.6115. Min Act: -0.0000

Data Index: 288461 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1622379 (Python Code)

Max Activating Token Index: 760

Text #5

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1015155 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1286351 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5381. Min Act: -0.0000

Data Index: 322891 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1553940 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1553568 (Python Code)

Max Activating Token Index: 961

Text #10

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1146804 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5107. Min Act: -0.0000

Data Index: 264234 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1493286 (Python Code)

Max Activating Token Index: 629

Text #13

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3989. Min Act: -0.0000

Data Index: 1654761 (Python Code)

Max Activating Token Index: 226

Text #14

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5264. Min Act: -0.0000

Data Index: 2632 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1332730 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1446617 (Python Code)

Max Activating Token Index: 792

Text #17

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1007171 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1072712 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.4782. Min Act: -0.0000

Data Index: 925813 (C4 (Web Text))

Max Activating Token Index: 237