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

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

Neuron 4167 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4905. Min Range: -2.4905

Max Act: 2.4905. Min Act: -0.0000

Data Index: 115285 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 2.4905. Min Range: -2.4905

Max Act: 2.0618. Min Act: -0.0000

Data Index: 495857 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 2.4905. Min Range: -2.4905

Max Act: 1.9428. Min Act: -0.0000

Data Index: 363106 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 2.4905. Min Range: -2.4905

Max Act: 1.4307. Min Act: -0.0000

Data Index: 966601 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 2.4905. Min Range: -2.4905

Max Act: 1.4357. Min Act: -0.0000

Data Index: 605107 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.8723. Min Act: -0.0000

Data Index: 946680 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 2.4905. Min Range: -2.4905

Max Act: 1.1307. Min Act: -0.0000

Data Index: 134129 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 2.4905. Min Range: -2.4905

Max Act: 1.1699. Min Act: -0.0000

Data Index: 463040 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 2.4905. Min Range: -2.4905

Max Act: 1.0530. Min Act: -0.0000

Data Index: 289657 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 2.4905. Min Range: -2.4905

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1410016 (Python Code)

Max Activating Token Index: 901

Text #10

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1168059 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.9820. Min Act: -0.0000

Data Index: 458932 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 2.4905. Min Range: -2.4905

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1495092 (Python Code)

Max Activating Token Index: 961

Text #13

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.9471. Min Act: -0.0000

Data Index: 45251 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1608497 (Python Code)

Max Activating Token Index: 488

Text #15

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.9210. Min Act: -0.0000

Data Index: 165706 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.8602. Min Act: -0.0000

Data Index: 217466 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1520519 (Python Code)

Max Activating Token Index: 716

Text #18

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1291463 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 2.4905. Min Range: -2.4905

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1466632 (Python Code)

Max Activating Token Index: 133