Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 60 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1681. Min Act: -0.0002

Data Index: 538479 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1468. Min Act: -0.0002

Data Index: 677112 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1328. Min Act: -0.0002

Data Index: 799492 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1490. Min Act: -0.0002

Data Index: 88074 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1341. Min Act: -0.0002

Data Index: 55145 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1422. Min Act: -0.0002

Data Index: 571130 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1468. Min Act: -0.0002

Data Index: 345522 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1415. Min Act: -0.0002

Data Index: 1201550 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1421. Min Act: -0.0002

Data Index: 991675 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1415. Min Act: -0.0002

Data Index: 1115991 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1401. Min Act: -0.0002

Data Index: 497573 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1392. Min Act: -0.0002

Data Index: 1111713 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1392. Min Act: -0.0002

Data Index: 849830 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1298. Min Act: -0.0002

Data Index: 572940 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1351. Min Act: -0.0002

Data Index: 346108 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1429. Min Act: -0.0002

Data Index: 307017 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1303. Min Act: -0.0002

Data Index: 302351 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1288. Min Act: -0.0002

Data Index: 751465 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1336. Min Act: -0.0002

Data Index: 1311691 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1285. Min Act: -0.0002

Data Index: 412051 (C4 (Web Text))

Max Activating Token Index: 1017