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

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

Neuron 436 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8501. Min Act: -0.0000

Data Index: 1391850 (Python Code)

Max Activating Token Index: 431

Text #1

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1462172 (Python Code)

Max Activating Token Index: 706

Text #2

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1478065 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1606053 (Python Code)

Max Activating Token Index: 564

Text #4

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1488895 (Python Code)

Max Activating Token Index: 555

Text #5

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1514970 (Python Code)

Max Activating Token Index: 978

Text #6

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1447818 (Python Code)

Max Activating Token Index: 171

Text #7

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1475540 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1589221 (Python Code)

Max Activating Token Index: 759

Text #9

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6703. Min Act: -0.0000

Data Index: 1556944 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1645647 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1369463 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1370505 (Python Code)

Max Activating Token Index: 383

Text #13

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1531756 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1560826 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1399597 (Python Code)

Max Activating Token Index: 1021

Text #16

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1601129 (Python Code)

Max Activating Token Index: 229

Text #17

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1402329 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1413156 (Python Code)

Max Activating Token Index: 384

Text #19

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1527478 (Python Code)

Max Activating Token Index: 483