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

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

Neuron 3498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0768. Min Range: -1.0768

Max Act: 1.0768. Min Act: -0.0000

Data Index: 1406311 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1620984 (Python Code)

Max Activating Token Index: 481

Text #2

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1585388 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1442322 (Python Code)

Max Activating Token Index: 234

Text #4

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1599816 (Python Code)

Max Activating Token Index: 1017

Text #5

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1417757 (Python Code)

Max Activating Token Index: 560

Text #6

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1405294 (Python Code)

Max Activating Token Index: 795

Text #7

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.7760. Min Act: -0.0001

Data Index: 1237908 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6466. Min Act: -0.0001

Data Index: 167272 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6862. Min Act: -0.0001

Data Index: 987487 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1406173 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1518291 (Python Code)

Max Activating Token Index: 846

Text #12

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1614400 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1586016 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6015. Min Act: -0.0001

Data Index: 1214598 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1405879 (Python Code)

Max Activating Token Index: 712

Text #16

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1448531 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1487621 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1377258 (Python Code)

Max Activating Token Index: 284

Text #19

Max Range: 1.0768. Min Range: -1.0768

Max Act: 0.6433. Min Act: -0.0001

Data Index: 189817 (C4 (Web Text))

Max Activating Token Index: 190