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

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

Neuron 4296 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: 4.7779. Min Range: -4.7779

Max Act: 4.7779. Min Act: -0.0000

Data Index: 1487579 (Python Code)

Max Activating Token Index: 485

Text #1

Max Range: 4.7779. Min Range: -4.7779

Max Act: 4.6840. Min Act: -0.0000

Data Index: 1465584 (Python Code)

Max Activating Token Index: 712

Text #2

Max Range: 4.7779. Min Range: -4.7779

Max Act: 4.6216. Min Act: -0.0000

Data Index: 1391254 (Python Code)

Max Activating Token Index: 604

Text #3

Max Range: 4.7779. Min Range: -4.7779

Max Act: 4.5730. Min Act: -0.0000

Data Index: 1624988 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 4.7779. Min Range: -4.7779

Max Act: 4.7483. Min Act: -0.0000

Data Index: 1387910 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 4.7779. Min Range: -4.7779

Max Act: 4.2640. Min Act: -0.0000

Data Index: 1636605 (Python Code)

Max Activating Token Index: 650

Text #6

Max Range: 4.7779. Min Range: -4.7779

Max Act: 4.2757. Min Act: -0.0000

Data Index: 1439631 (Python Code)

Max Activating Token Index: 730

Text #7

Max Range: 4.7779. Min Range: -4.7779

Max Act: 4.1355. Min Act: -0.0000

Data Index: 1483973 (Python Code)

Max Activating Token Index: 104

Text #8

Max Range: 4.7779. Min Range: -4.7779

Max Act: 4.0560. Min Act: -0.0000

Data Index: 1583763 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.8757. Min Act: -0.0000

Data Index: 1519712 (Python Code)

Max Activating Token Index: 638

Text #10

Max Range: 4.7779. Min Range: -4.7779

Max Act: 4.0139. Min Act: -0.0000

Data Index: 1541772 (Python Code)

Max Activating Token Index: 326

Text #11

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.8151. Min Act: -0.0000

Data Index: 1509436 (Python Code)

Max Activating Token Index: 319

Text #12

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.9464. Min Act: -0.0000

Data Index: 1512151 (Python Code)

Max Activating Token Index: 411

Text #13

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.8671. Min Act: -0.0000

Data Index: 1393503 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.8324. Min Act: -0.0000

Data Index: 1554679 (Python Code)

Max Activating Token Index: 629

Text #15

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.6833. Min Act: -0.0000

Data Index: 1627668 (Python Code)

Max Activating Token Index: 584

Text #16

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.8128. Min Act: -0.0000

Data Index: 1566709 (Python Code)

Max Activating Token Index: 98

Text #17

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.7850. Min Act: -0.0000

Data Index: 1535622 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.7274. Min Act: -0.0000

Data Index: 1508642 (Python Code)

Max Activating Token Index: 400

Text #19

Max Range: 4.7779. Min Range: -4.7779

Max Act: 3.7421. Min Act: -0.0000

Data Index: 1517401 (Python Code)

Max Activating Token Index: 81