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

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

Neuron 977 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: 0.2032. Min Range: -0.2032

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1292126 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1900. Min Act: -0.0000

Data Index: 291983 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1758. Min Act: -0.0000

Data Index: 115045 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1240377 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1801. Min Act: -0.0000

Data Index: 281903 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1619933 (Python Code)

Max Activating Token Index: 281

Text #6

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1506678 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1137754 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1448. Min Act: -0.0000

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1426. Min Act: -0.0000

Data Index: 270347 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1499606 (Python Code)

Max Activating Token Index: 976

Text #11

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1200084 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1567714 (Python Code)

Max Activating Token Index: 212

Text #13

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1428. Min Act: -0.0000

Data Index: 738963 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1581667 (Python Code)

Max Activating Token Index: 419

Text #15

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1394. Min Act: -0.0000

Data Index: 716811 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1274. Min Act: -0.0000

Data Index: 171293 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1294. Min Act: -0.0000

Data Index: 714653 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1211. Min Act: -0.0000

Data Index: 942180 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.2032. Min Range: -0.2032

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1503672 (Python Code)

Max Activating Token Index: 589