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

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

Neuron 1710 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1375. Min Range: -1.1375

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1603577 (Python Code)

Max Activating Token Index: 176

Text #1

Max Range: 1.1375. Min Range: -1.1375

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1607393 (Python Code)

Max Activating Token Index: 469

Text #2

Max Range: 1.1375. Min Range: -1.1375

Max Act: 1.1053. Min Act: -0.0000

Data Index: 1515219 (Python Code)

Max Activating Token Index: 650

Text #3

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.9970. Min Act: -0.0000

Data Index: 1520092 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1536840 (Python Code)

Max Activating Token Index: 234

Text #5

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1523220 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1417337 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1478749 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1471229 (Python Code)

Max Activating Token Index: 449

Text #9

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1541856 (Python Code)

Max Activating Token Index: 455

Text #10

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1593908 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1390524 (Python Code)

Max Activating Token Index: 354

Text #12

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1574001 (Python Code)

Max Activating Token Index: 671

Text #13

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1382268 (Python Code)

Max Activating Token Index: 323

Text #14

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8969. Min Act: -0.0000

Data Index: 1424945 (Python Code)

Max Activating Token Index: 429

Text #15

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1539104 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1456661 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8937. Min Act: -0.0000

Data Index: 1572787 (Python Code)

Max Activating Token Index: 347

Text #18

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1443403 (Python Code)

Max Activating Token Index: 417

Text #19

Max Range: 1.1375. Min Range: -1.1375

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1565226 (Python Code)

Max Activating Token Index: 876