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

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

Neuron 504 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: 0.2467. Min Range: -0.2467

Max Act: 0.2467. Min Act: -0.0001

Data Index: 941280 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.2107. Min Act: -0.0001

Data Index: 648806 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1861. Min Act: -0.0001

Data Index: 1287288 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1725. Min Act: -0.0001

Data Index: 440534 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1700. Min Act: -0.0001

Data Index: 504417 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1618. Min Act: -0.0001

Data Index: 630530 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1182837 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1607. Min Act: -0.0001

Data Index: 246169 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1415935 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1551. Min Act: -0.0000

Data Index: 927515 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1494. Min Act: -0.0001

Data Index: 844747 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1528. Min Act: -0.0000

Data Index: 261460 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1523. Min Act: -0.0001

Data Index: 937316 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1438. Min Act: -0.0001

Data Index: 415669 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1373. Min Act: -0.0000

Data Index: 509551 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1486. Min Act: -0.0001

Data Index: 293115 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1307016 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1302549 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1346. Min Act: -0.0001

Data Index: 243245 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.2467. Min Range: -0.2467

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1236725 (C4 (Web Text))

Max Activating Token Index: 840