Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3307 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.8669. Min Act: -0.0001

Data Index: 1601274 (Python Code)

Max Activating Token Index: 439

Text #1

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.8123. Min Act: -0.0001

Data Index: 1473431 (Python Code)

Max Activating Token Index: 638

Text #2

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.7617. Min Act: -0.0001

Data Index: 1622995 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.7506. Min Act: -0.0001

Data Index: 1434736 (Python Code)

Max Activating Token Index: 106

Text #4

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.6870. Min Act: -0.0001

Data Index: 1478712 (Python Code)

Max Activating Token Index: 718

Text #5

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.6839. Min Act: -0.0001

Data Index: 1477827 (Python Code)

Max Activating Token Index: 752

Text #6

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.6769. Min Act: -0.0001

Data Index: 1362726 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.5837. Min Act: -0.0001

Data Index: 1508630 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.5537. Min Act: -0.0001

Data Index: 1380067 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.5441. Min Act: -0.0001

Data Index: 1609628 (Python Code)

Max Activating Token Index: 753

Text #10

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.4831. Min Act: -0.0001

Data Index: 1493362 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.5667. Min Act: -0.0001

Data Index: 1389836 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.4710. Min Act: -0.0001

Data Index: 1506251 (Python Code)

Max Activating Token Index: 113

Text #13

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.5567. Min Act: -0.0001

Data Index: 1634767 (Python Code)

Max Activating Token Index: 298

Text #14

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.5372. Min Act: -0.0001

Data Index: 1412972 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.5307. Min Act: -0.0001

Data Index: 1631641 (Python Code)

Max Activating Token Index: 564

Text #16

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.5216. Min Act: -0.0001

Data Index: 1530423 (Python Code)

Max Activating Token Index: 358

Text #17

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.4804. Min Act: -0.0001

Data Index: 1399215 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.4651. Min Act: -0.0001

Data Index: 1617159 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 1.8669. Min Range: -1.8669

Max Act: 1.3910. Min Act: -0.0001

Data Index: 1577374 (Python Code)

Max Activating Token Index: 700