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

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

Neuron 671 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: 0.8439. Min Range: -0.8439

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1553449 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1604272 (Python Code)

Max Activating Token Index: 818

Text #2

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1493419 (Python Code)

Max Activating Token Index: 84

Text #3

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1374299 (Python Code)

Max Activating Token Index: 963

Text #4

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1443239 (Python Code)

Max Activating Token Index: 273

Text #5

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1651810 (Python Code)

Max Activating Token Index: 897

Text #6

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1458729 (Python Code)

Max Activating Token Index: 171

Text #7

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1635600 (Python Code)

Max Activating Token Index: 1006

Text #8

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1655826 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1375161 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1435243 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1421729 (Python Code)

Max Activating Token Index: 520

Text #12

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1448978 (Python Code)

Max Activating Token Index: 833

Text #13

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1478607 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1525013 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1457519 (Python Code)

Max Activating Token Index: 764

Text #16

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1373354 (Python Code)

Max Activating Token Index: 245

Text #17

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1476000 (Python Code)

Max Activating Token Index: 364

Text #18

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1564262 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 0.8439. Min Range: -0.8439

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1393118 (Python Code)

Max Activating Token Index: 421