Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2386 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0716. Min Act: -0.0004

Data Index: 1538999 (Python Code)

Max Activating Token Index: 28

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0646. Min Act: -0.0004

Data Index: 1446793 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0004

Data Index: 1649634 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0671. Min Act: -0.0004

Data Index: 1534658 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0689. Min Act: -0.0004

Data Index: 1622967 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0658. Min Act: -0.0004

Data Index: 1547640 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0649. Min Act: -0.0004

Data Index: 1400543 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0649. Min Act: -0.0004

Data Index: 1629127 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0673. Min Act: -0.0004

Data Index: 1613119 (Python Code)

Max Activating Token Index: 1003

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0622. Min Act: -0.0004

Data Index: 1501363 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0611. Min Act: -0.0004

Data Index: 1378364 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0602. Min Act: -0.0004

Data Index: 1528751 (Python Code)

Max Activating Token Index: 120

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0648. Min Act: -0.0004

Data Index: 1360361 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0599. Min Act: -0.0004

Data Index: 1506572 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0647. Min Act: -0.0004

Data Index: 1375674 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0646. Min Act: -0.0004

Data Index: 1652396 (Python Code)

Max Activating Token Index: 695

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0597. Min Act: -0.0004

Data Index: 1557575 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0620. Min Act: -0.0004

Data Index: 1655874 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0617. Min Act: -0.0004

Data Index: 1532758 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0590. Min Act: -0.0004

Data Index: 1406222 (Python Code)

Max Activating Token Index: 43