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

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

Neuron 2559 in Layer 1

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: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1599822 (Python Code)

Max Activating Token Index: 36

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1638927 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1521688 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1467030 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1601759 (Python Code)

Max Activating Token Index: 212

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1468785 (Python Code)

Max Activating Token Index: 208

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1613161 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1510363 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1439977 (Python Code)

Max Activating Token Index: 738

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1362904 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0460. Min Act: -0.0002

Data Index: 1608405 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1545944 (Python Code)

Max Activating Token Index: 107

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1458848 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1554156 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1469230 (Python Code)

Max Activating Token Index: 660

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1462959 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1375515 (Python Code)

Max Activating Token Index: 400

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1409556 (Python Code)

Max Activating Token Index: 1019

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1534012 (Python Code)

Max Activating Token Index: 58

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1583836 (Python Code)

Max Activating Token Index: 687