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

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

Neuron 4185 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.7241. Min Act: -0.0001

Data Index: 1565950 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6436. Min Act: -0.0001

Data Index: 1588675 (Python Code)

Max Activating Token Index: 369

Text #2

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1635532 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6589. Min Act: -0.0001

Data Index: 1543334 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6590. Min Act: -0.0001

Data Index: 1492006 (Python Code)

Max Activating Token Index: 39

Text #5

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6742. Min Act: -0.0001

Data Index: 1569038 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6258. Min Act: -0.0001

Data Index: 1467465 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6486. Min Act: -0.0001

Data Index: 1469479 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.5918. Min Act: -0.0001

Data Index: 1559077 (Python Code)

Max Activating Token Index: 177

Text #9

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6452. Min Act: -0.0001

Data Index: 1382154 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6398. Min Act: -0.0001

Data Index: 1469208 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6386. Min Act: -0.0001

Data Index: 1589659 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6328. Min Act: -0.0001

Data Index: 1396890 (Python Code)

Max Activating Token Index: 360

Text #13

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6354. Min Act: -0.0001

Data Index: 1470589 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6054. Min Act: -0.0001

Data Index: 1443185 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6311. Min Act: -0.0001

Data Index: 1477830 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6448. Min Act: -0.0001

Data Index: 1360663 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6265. Min Act: -0.0001

Data Index: 1646787 (Python Code)

Max Activating Token Index: 439

Text #18

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6099. Min Act: -0.0001

Data Index: 1512735 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 0.7241. Min Range: -0.7241

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1552411 (Python Code)

Max Activating Token Index: 5