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

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

Neuron 628 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.8193. Min Act: 0.0000

Data Index: 1433459 (Python Code)

Max Activating Token Index: 335

Text #1

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7683. Min Act: 0.0000

Data Index: 1485909 (Python Code)

Max Activating Token Index: 998

Text #2

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.8007. Min Act: 0.0000

Data Index: 1401309 (Python Code)

Max Activating Token Index: 611

Text #3

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1481550 (Python Code)

Max Activating Token Index: 832

Text #4

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1420475 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1624486 (Python Code)

Max Activating Token Index: 850

Text #6

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1526116 (Python Code)

Max Activating Token Index: 960

Text #7

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7272. Min Act: 0.0000

Data Index: 1379260 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7599. Min Act: -0.0000

Data Index: 191721 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6984. Min Act: 0.0000

Data Index: 1617893 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1545611 (Python Code)

Max Activating Token Index: 615

Text #11

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7002. Min Act: 0.0000

Data Index: 1593471 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1370843 (Python Code)

Max Activating Token Index: 418

Text #13

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6819. Min Act: 0.0000

Data Index: 1106863 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6735. Min Act: 0.0000

Data Index: 1362671 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6822. Min Act: 0.0000

Data Index: 1603867 (Python Code)

Max Activating Token Index: 383

Text #16

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1404108 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.7077. Min Act: 0.0000

Data Index: 1471557 (Python Code)

Max Activating Token Index: 321

Text #18

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6999. Min Act: 0.0000

Data Index: 1367313 (Python Code)

Max Activating Token Index: 598

Text #19

Max Range: 0.8193. Min Range: -0.8193

Max Act: 0.6904. Min Act: 0.0000

Data Index: 1490830 (Python Code)

Max Activating Token Index: 684