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

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

Neuron 607 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.9452. Min Act: -0.0001

Data Index: 643594 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.7659. Min Act: -0.0001

Data Index: 1439263 (Python Code)

Max Activating Token Index: 117

Text #2

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.8958. Min Act: -0.0001

Data Index: 1462130 (Python Code)

Max Activating Token Index: 590

Text #3

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.8009. Min Act: -0.0001

Data Index: 88657 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.8291. Min Act: -0.0001

Data Index: 1237826 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.8628. Min Act: -0.0001

Data Index: 1604647 (Python Code)

Max Activating Token Index: 654

Text #6

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.6939. Min Act: -0.0001

Data Index: 1551935 (Python Code)

Max Activating Token Index: 993

Text #7

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.7852. Min Act: -0.0001

Data Index: 1647648 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.5868. Min Act: -0.0001

Data Index: 1434883 (Python Code)

Max Activating Token Index: 830

Text #9

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.7726. Min Act: -0.0001

Data Index: 1415601 (Python Code)

Max Activating Token Index: 535

Text #10

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.7426. Min Act: -0.0001

Data Index: 557810 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.7373. Min Act: -0.0001

Data Index: 1609569 (Python Code)

Max Activating Token Index: 326

Text #12

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.6317. Min Act: -0.0001

Data Index: 1598906 (Python Code)

Max Activating Token Index: 828

Text #13

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.6436. Min Act: -0.0001

Data Index: 1360319 (Python Code)

Max Activating Token Index: 601

Text #14

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.7026. Min Act: -0.0001

Data Index: 1612631 (Python Code)

Max Activating Token Index: 582

Text #15

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.5853. Min Act: -0.0001

Data Index: 1595643 (Python Code)

Max Activating Token Index: 207

Text #16

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.6619. Min Act: -0.0001

Data Index: 1528679 (Python Code)

Max Activating Token Index: 238

Text #17

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.6667. Min Act: -0.0001

Data Index: 327817 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.6549. Min Act: -0.0001

Data Index: 1128650 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 1.9452. Min Range: -1.9452

Max Act: 1.8066. Min Act: -0.0001

Data Index: 729138 (C4 (Web Text))

Max Activating Token Index: 896