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

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

Neuron 854 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1381793 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0709. Min Act: -0.0003

Data Index: 1515267 (Python Code)

Max Activating Token Index: 279

Text #2

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0703. Min Act: -0.0003

Data Index: 276430 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1377648 (Python Code)

Max Activating Token Index: 730

Text #4

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0705. Min Act: -0.0003

Data Index: 1419286 (Python Code)

Max Activating Token Index: 686

Text #5

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0718. Min Act: -0.0003

Data Index: 945747 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1492666 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1368686 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0691. Min Act: -0.0003

Data Index: 1590653 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0679. Min Act: -0.0003

Data Index: 881272 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1650494 (Python Code)

Max Activating Token Index: 263

Text #11

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0661. Min Act: -0.0003

Data Index: 1455433 (Python Code)

Max Activating Token Index: 353

Text #12

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1500499 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1418782 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0653. Min Act: -0.0003

Data Index: 1383300 (Python Code)

Max Activating Token Index: 699

Text #15

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1615742 (Python Code)

Max Activating Token Index: 268

Text #16

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1377056 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1462638 (Python Code)

Max Activating Token Index: 226

Text #18

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0648. Min Act: -0.0003

Data Index: 969913 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1635054 (Python Code)

Max Activating Token Index: 253