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

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

Neuron 3903 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1607. Min Range: -3.1607

Max Act: 3.1607. Min Act: -0.0000

Data Index: 1375211 (Python Code)

Max Activating Token Index: 205

Text #1

Max Range: 3.1607. Min Range: -3.1607

Max Act: 2.7964. Min Act: -0.0000

Data Index: 1536680 (Python Code)

Max Activating Token Index: 480

Text #2

Max Range: 3.1607. Min Range: -3.1607

Max Act: 2.7810. Min Act: -0.0000

Data Index: 1485501 (Python Code)

Max Activating Token Index: 183

Text #3

Max Range: 3.1607. Min Range: -3.1607

Max Act: 2.7316. Min Act: -0.0000

Data Index: 1438038 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 3.1607. Min Range: -3.1607

Max Act: 2.4852. Min Act: -0.0000

Data Index: 1510772 (Python Code)

Max Activating Token Index: 445

Text #5

Max Range: 3.1607. Min Range: -3.1607

Max Act: 2.6682. Min Act: -0.0000

Data Index: 1542111 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 3.1607. Min Range: -3.1607

Max Act: 2.6862. Min Act: -0.0000

Data Index: 1531831 (Python Code)

Max Activating Token Index: 388

Text #7

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.7581. Min Act: -0.0000

Data Index: 1138107 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.9797. Min Act: -0.0000

Data Index: 1439862 (Python Code)

Max Activating Token Index: 477

Text #9

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.9505. Min Act: -0.0000

Data Index: 1646435 (Python Code)

Max Activating Token Index: 795

Text #10

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.7608. Min Act: -0.0000

Data Index: 1603010 (Python Code)

Max Activating Token Index: 551

Text #11

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1536353 (Python Code)

Max Activating Token Index: 164

Text #12

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.6436. Min Act: -0.0000

Data Index: 1544275 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.5692. Min Act: -0.0000

Data Index: 1641804 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.5310. Min Act: -0.0000

Data Index: 1629758 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1587055 (Python Code)

Max Activating Token Index: 167

Text #16

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1410507 (Python Code)

Max Activating Token Index: 217

Text #17

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.5904. Min Act: -0.0000

Data Index: 219472 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.4665. Min Act: -0.0000

Data Index: 444028 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 3.1607. Min Range: -3.1607

Max Act: 1.4970. Min Act: -0.0000

Data Index: 1467219 (Python Code)

Max Activating Token Index: 251