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

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

Neuron 2873 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1895. Min Act: -0.0000

Data Index: 317246 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1697. Min Act: -0.0000

Data Index: 386708 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1666. Min Act: -0.0000

Data Index: 637146 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1495. Min Act: -0.0000

Data Index: 625024 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1569. Min Act: -0.0000

Data Index: 106524 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1499. Min Act: -0.0000

Data Index: 486127 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1522. Min Act: -0.0000

Data Index: 437926 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1212354 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1131429 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1564. Min Act: -0.0000

Data Index: 429351 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1665. Min Act: -0.0000

Data Index: 364467 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1467. Min Act: -0.0000

Data Index: 245406 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1252877 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1510. Min Act: -0.0000

Data Index: 484693 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1210721 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1524. Min Act: -0.0000

Data Index: 704016 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1518. Min Act: -0.0000

Data Index: 645537 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1125684 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1263442 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.1895. Min Range: -0.1895

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1323417 (C4 (Web Text))

Max Activating Token Index: 382