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

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

Neuron 3511 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: 1.6515. Min Range: -1.6515

Max Act: 1.6515. Min Act: -0.0000

Data Index: 1493757 (Python Code)

Max Activating Token Index: 354

Text #1

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1580548 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1471143 (Python Code)

Max Activating Token Index: 223

Text #3

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1527527 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1495526 (Python Code)

Max Activating Token Index: 194

Text #5

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1478771 (Python Code)

Max Activating Token Index: 561

Text #6

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1573462 (Python Code)

Max Activating Token Index: 206

Text #7

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1501711 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1413423 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1416681 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1374258 (Python Code)

Max Activating Token Index: 349

Text #11

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.6606. Min Act: 0.0000

Data Index: 1538384 (Python Code)

Max Activating Token Index: 421

Text #12

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1445699 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1386381 (Python Code)

Max Activating Token Index: 198

Text #14

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1540292 (Python Code)

Max Activating Token Index: 267

Text #15

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.6295. Min Act: 0.0000

Data Index: 1614446 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1620853 (Python Code)

Max Activating Token Index: 996

Text #17

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1485900 (Python Code)

Max Activating Token Index: 442

Text #18

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1604802 (Python Code)

Max Activating Token Index: 236

Text #19

Max Range: 1.6515. Min Range: -1.6515

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1496503 (Python Code)

Max Activating Token Index: 606