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

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

Neuron 529 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.8075. Min Act: -0.0001

Data Index: 1565774 (Python Code)

Max Activating Token Index: 748

Text #1

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7864. Min Act: -0.0001

Data Index: 1646858 (Python Code)

Max Activating Token Index: 600

Text #2

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6876. Min Act: -0.0001

Data Index: 1436034 (Python Code)

Max Activating Token Index: 693

Text #3

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6989. Min Act: -0.0001

Data Index: 1382368 (Python Code)

Max Activating Token Index: 987

Text #4

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7278. Min Act: -0.0001

Data Index: 1518622 (Python Code)

Max Activating Token Index: 775

Text #5

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6570. Min Act: -0.0001

Data Index: 1417868 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6758. Min Act: -0.0001

Data Index: 1644862 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6707. Min Act: -0.0001

Data Index: 1559912 (Python Code)

Max Activating Token Index: 353

Text #8

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6493. Min Act: -0.0001

Data Index: 1373647 (Python Code)

Max Activating Token Index: 626

Text #9

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6405. Min Act: -0.0001

Data Index: 1481454 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6494. Min Act: -0.0001

Data Index: 1609046 (Python Code)

Max Activating Token Index: 141

Text #11

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6776. Min Act: -0.0001

Data Index: 1573022 (Python Code)

Max Activating Token Index: 127

Text #12

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1449006 (Python Code)

Max Activating Token Index: 477

Text #13

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6489. Min Act: -0.0001

Data Index: 1594997 (Python Code)

Max Activating Token Index: 203

Text #14

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6655. Min Act: -0.0001

Data Index: 1452412 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6411. Min Act: -0.0001

Data Index: 1433606 (Python Code)

Max Activating Token Index: 753

Text #16

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6382. Min Act: -0.0001

Data Index: 1395108 (Python Code)

Max Activating Token Index: 465

Text #17

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6052. Min Act: -0.0001

Data Index: 1652909 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6000. Min Act: -0.0001

Data Index: 1472800 (Python Code)

Max Activating Token Index: 859

Text #19

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6401. Min Act: -0.0001

Data Index: 1533164 (Python Code)

Max Activating Token Index: 57