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

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

Neuron 5813 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1365759 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1489943 (Python Code)

Max Activating Token Index: 185

Text #2

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1541276 (Python Code)

Max Activating Token Index: 123

Text #3

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1637660 (Python Code)

Max Activating Token Index: 911

Text #4

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1510040 (Python Code)

Max Activating Token Index: 928

Text #5

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1536780 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1463484 (Python Code)

Max Activating Token Index: 400

Text #7

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1520580 (Python Code)

Max Activating Token Index: 366

Text #8

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1580216 (Python Code)

Max Activating Token Index: 240

Text #9

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1518199 (Python Code)

Max Activating Token Index: 787

Text #10

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1643704 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1584866 (Python Code)

Max Activating Token Index: 204

Text #12

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1613948 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0702. Min Act: -0.0001

Data Index: 1499693 (Python Code)

Max Activating Token Index: 986

Text #14

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1462768 (Python Code)

Max Activating Token Index: 99

Text #15

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1594181 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1641244 (Python Code)

Max Activating Token Index: 353

Text #17

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1472948 (Python Code)

Max Activating Token Index: 67

Text #18

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1396667 (Python Code)

Max Activating Token Index: 709

Text #19

Max Range: 0.1013. Min Range: -0.1013

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1587411 (Python Code)

Max Activating Token Index: 528