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

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

Neuron 4881 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3753. Min Range: -3.3753

Max Act: 3.3753. Min Act: -0.0000

Data Index: 651371 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.5680. Min Act: -0.0000

Data Index: 1315413 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.2576. Min Act: -0.0000

Data Index: 459209 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.3477. Min Act: -0.0000

Data Index: 1019882 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1134. Min Act: -0.0000

Data Index: 110454 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.3059. Min Act: -0.0000

Data Index: 38392 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.2964. Min Act: -0.0000

Data Index: 317161 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.3055. Min Act: -0.0000

Data Index: 228702 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1252. Min Act: -0.0000

Data Index: 824435 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1215. Min Act: -0.0000

Data Index: 1338231 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1117. Min Act: -0.0000

Data Index: 236683 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.3426. Min Act: -0.0000

Data Index: 64813 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1337. Min Act: -0.0000

Data Index: 502329 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1388. Min Act: -0.0000

Data Index: 112613 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1319. Min Act: -0.0000

Data Index: 1337370 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1123. Min Act: -0.0000

Data Index: 1224789 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1150. Min Act: -0.0000

Data Index: 583174 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1038. Min Act: -0.0000

Data Index: 585709 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.1005. Min Act: -0.0000

Data Index: 1137186 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 3.3753. Min Range: -3.3753

Max Act: 2.0058. Min Act: -0.0000

Data Index: 1111463 (C4 (Web Text))

Max Activating Token Index: 262