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

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

Neuron 4841 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: 1.5278. Min Range: -1.5278

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1539410 (Python Code)

Max Activating Token Index: 885

Text #1

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.5278. Min Act: -0.0000

Data Index: 1397699 (Python Code)

Max Activating Token Index: 233

Text #2

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1603591 (Python Code)

Max Activating Token Index: 947

Text #3

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1370727 (Python Code)

Max Activating Token Index: 618

Text #4

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.3115. Min Act: -0.0000

Data Index: 1497873 (Python Code)

Max Activating Token Index: 554

Text #5

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1411296 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1531470 (Python Code)

Max Activating Token Index: 611

Text #7

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.2197. Min Act: -0.0000

Data Index: 1543687 (Python Code)

Max Activating Token Index: 219

Text #8

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1574034 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1379. Min Act: -0.0000

Data Index: 1364953 (Python Code)

Max Activating Token Index: 467

Text #10

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1637584 (Python Code)

Max Activating Token Index: 978

Text #11

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1621289 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1454348 (Python Code)

Max Activating Token Index: 365

Text #13

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0867. Min Act: -0.0000

Data Index: 942765 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0551. Min Act: -0.0000

Data Index: 1581649 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1602134 (Python Code)

Max Activating Token Index: 271

Text #16

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1416902 (Python Code)

Max Activating Token Index: 427

Text #17

Max Range: 1.5278. Min Range: -1.5278

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1364001 (Python Code)

Max Activating Token Index: 444

Text #18

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1474173 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 1.5278. Min Range: -1.5278

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1426511 (Python Code)

Max Activating Token Index: 792