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

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

Neuron 303 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1410096 (Python Code)

Max Activating Token Index: 4

Text #1

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1379731 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1465446 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7195. Min Act: -0.0001

Data Index: 1547958 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7195. Min Act: -0.0001

Data Index: 1564800 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7195. Min Act: -0.0001

Data Index: 1408586 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1552941 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.7063. Min Act: -0.0001

Data Index: 1375095 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6468. Min Act: -0.0001

Data Index: 1457745 (Python Code)

Max Activating Token Index: 517

Text #9

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6630. Min Act: -0.0001

Data Index: 1570893 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6630. Min Act: -0.0001

Data Index: 1576498 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6409. Min Act: -0.0001

Data Index: 1478860 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6386. Min Act: -0.0001

Data Index: 1399392 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6344. Min Act: -0.0001

Data Index: 1487906 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5821. Min Act: -0.0001

Data Index: 1394387 (Python Code)

Max Activating Token Index: 906

Text #15

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6121. Min Act: -0.0001

Data Index: 1383416 (Python Code)

Max Activating Token Index: 800

Text #16

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6399. Min Act: -0.0001

Data Index: 1615380 (Python Code)

Max Activating Token Index: 814

Text #17

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1385100 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5345. Min Act: -0.0001

Data Index: 1426086 (Python Code)

Max Activating Token Index: 367

Text #19

Max Range: 0.8006. Min Range: -0.8006

Max Act: 0.5419. Min Act: -0.0001

Data Index: 1620104 (Python Code)

Max Activating Token Index: 825