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

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

Neuron 5225 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: 2.1468. Min Range: -2.1468

Max Act: 2.1468. Min Act: -0.0000

Data Index: 1442546 (Python Code)

Max Activating Token Index: 406

Text #1

Max Range: 2.1468. Min Range: -2.1468

Max Act: 1.5343. Min Act: -0.0000

Data Index: 1547834 (Python Code)

Max Activating Token Index: 215

Text #2

Max Range: 2.1468. Min Range: -2.1468

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1635961 (Python Code)

Max Activating Token Index: 760

Text #3

Max Range: 2.1468. Min Range: -2.1468

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1498908 (Python Code)

Max Activating Token Index: 261

Text #4

Max Range: 2.1468. Min Range: -2.1468

Max Act: 1.0685. Min Act: -0.0001

Data Index: 1155545 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 2.1468. Min Range: -2.1468

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1577227 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 2.1468. Min Range: -2.1468

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1427270 (Python Code)

Max Activating Token Index: 270

Text #7

Max Range: 2.1468. Min Range: -2.1468

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1644947 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1439464 (Python Code)

Max Activating Token Index: 298

Text #9

Max Range: 2.1468. Min Range: -2.1468

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1478865 (Python Code)

Max Activating Token Index: 341

Text #10

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1634502 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 2.1468. Min Range: -2.1468

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1389569 (Python Code)

Max Activating Token Index: 486

Text #12

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.9156. Min Act: -0.0000

Data Index: 1506422 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1627663 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.7790. Min Act: -0.0000

Data Index: 1453127 (Python Code)

Max Activating Token Index: 228

Text #15

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1463299 (Python Code)

Max Activating Token Index: 664

Text #16

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1616085 (Python Code)

Max Activating Token Index: 353

Text #17

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1498421 (Python Code)

Max Activating Token Index: 321

Text #18

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1556778 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 2.1468. Min Range: -2.1468

Max Act: 0.7636. Min Act: -0.0001

Data Index: 1641870 (Python Code)

Max Activating Token Index: 206