Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4567 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0003

Data Index: 1615544 (Python Code)

Max Activating Token Index: 73

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0736. Min Act: -0.0003

Data Index: 1531171 (Python Code)

Max Activating Token Index: 962

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1465832 (Python Code)

Max Activating Token Index: 628

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1372883 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1569972 (Python Code)

Max Activating Token Index: 143

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1399905 (Python Code)

Max Activating Token Index: 470

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1377077 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1628578 (Python Code)

Max Activating Token Index: 89

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1410113 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1426451 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1546804 (Python Code)

Max Activating Token Index: 158

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1410734 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1572578 (Python Code)

Max Activating Token Index: 876

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1509679 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1435195 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1402717 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1602213 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1623053 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1404186 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0474. Min Act: -0.0003

Data Index: 1396180 (Python Code)

Max Activating Token Index: 341