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

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

Neuron 2418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.9932. Min Act: -0.0000

Data Index: 1369564 (Python Code)

Max Activating Token Index: 805

Text #1

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.9191. Min Act: -0.0000

Data Index: 1391185 (Python Code)

Max Activating Token Index: 247

Text #2

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.7477. Min Act: -0.0000

Data Index: 1505717 (Python Code)

Max Activating Token Index: 342

Text #3

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.5295. Min Act: -0.0000

Data Index: 1451326 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.6295. Min Act: -0.0000

Data Index: 1416450 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.7260. Min Act: -0.0000

Data Index: 1499908 (Python Code)

Max Activating Token Index: 657

Text #6

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.3113. Min Act: -0.0000

Data Index: 1396107 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.4034. Min Act: -0.0000

Data Index: 1425894 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.3761. Min Act: -0.0000

Data Index: 1579001 (Python Code)

Max Activating Token Index: 565

Text #9

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.2623. Min Act: -0.0000

Data Index: 1610858 (Python Code)

Max Activating Token Index: 984

Text #10

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.2666. Min Act: -0.0000

Data Index: 1546130 (Python Code)

Max Activating Token Index: 398

Text #11

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.0926. Min Act: -0.0000

Data Index: 1655607 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.2168. Min Act: -0.0000

Data Index: 1549261 (Python Code)

Max Activating Token Index: 843

Text #13

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.3709. Min Act: -0.0000

Data Index: 1500101 (Python Code)

Max Activating Token Index: 513

Text #14

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.2010. Min Act: -0.0000

Data Index: 1392446 (Python Code)

Max Activating Token Index: 552

Text #15

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.0396. Min Act: -0.0000

Data Index: 1448419 (Python Code)

Max Activating Token Index: 763

Text #16

Max Range: 3.9932. Min Range: -3.9932

Max Act: 2.8739. Min Act: -0.0000

Data Index: 1430858 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.3141. Min Act: -0.0000

Data Index: 1512463 (Python Code)

Max Activating Token Index: 306

Text #18

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.1342. Min Act: -0.0000

Data Index: 1514730 (Python Code)

Max Activating Token Index: 406

Text #19

Max Range: 3.9932. Min Range: -3.9932

Max Act: 3.4107. Min Act: -0.0000

Data Index: 1438747 (Python Code)

Max Activating Token Index: 897