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

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

Neuron 3382 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1604158 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1460219 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1518990 (Python Code)

Max Activating Token Index: 505

Text #3

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1541472 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7386. Min Act: -0.0000

Data Index: 1364173 (Python Code)

Max Activating Token Index: 843

Text #5

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1454211 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1620750 (Python Code)

Max Activating Token Index: 276

Text #7

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1373347 (Python Code)

Max Activating Token Index: 952

Text #8

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1644559 (Python Code)

Max Activating Token Index: 219

Text #9

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1382568 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1496931 (Python Code)

Max Activating Token Index: 860

Text #11

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1634739 (Python Code)

Max Activating Token Index: 127

Text #12

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1476605 (Python Code)

Max Activating Token Index: 51

Text #13

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1503321 (Python Code)

Max Activating Token Index: 370

Text #14

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1412167 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1618668 (Python Code)

Max Activating Token Index: 230

Text #16

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6039. Min Act: -0.0000

Data Index: 1517002 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1362054 (Python Code)

Max Activating Token Index: 577

Text #18

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1479339 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1632809 (Python Code)

Max Activating Token Index: 557