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

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

Neuron 498 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2435. Min Act: -0.0002

Data Index: 1392921 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2459. Min Act: -0.0001

Data Index: 1460341 (Python Code)

Max Activating Token Index: 557

Text #2

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2391. Min Act: 0.0000

Data Index: 1619130 (Python Code)

Max Activating Token Index: 1013

Text #3

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2352. Min Act: -0.0001

Data Index: 1433020 (Python Code)

Max Activating Token Index: 686

Text #4

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2166. Min Act: -0.0001

Data Index: 1559921 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2142. Min Act: -0.0001

Data Index: 1513382 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1454738 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1431245 (Python Code)

Max Activating Token Index: 54

Text #8

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1507236 (Python Code)

Max Activating Token Index: 958

Text #9

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1893. Min Act: -0.0001

Data Index: 1434137 (Python Code)

Max Activating Token Index: 774

Text #10

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1880. Min Act: -0.0001

Data Index: 1507751 (Python Code)

Max Activating Token Index: 979

Text #11

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1864. Min Act: -0.0001

Data Index: 1375070 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1897. Min Act: 0.0000

Data Index: 1377256 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1856. Min Act: -0.0001

Data Index: 1378685 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1581576 (Python Code)

Max Activating Token Index: 955

Text #15

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1845. Min Act: -0.0001

Data Index: 1551865 (Python Code)

Max Activating Token Index: 820

Text #16

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1542607 (Python Code)

Max Activating Token Index: 231

Text #17

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1752. Min Act: -0.0001

Data Index: 1423281 (Python Code)

Max Activating Token Index: 742

Text #18

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1828. Min Act: -0.0001

Data Index: 1425467 (Python Code)

Max Activating Token Index: 957

Text #19

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1622707 (Python Code)

Max Activating Token Index: 11