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

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

Neuron 2895 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0663. Min Act: -0.0003

Data Index: 338865 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0493. Min Act: -0.0003

Data Index: 951408 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1342615 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0450. Min Act: -0.0003

Data Index: 399919 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1141547 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0446. Min Act: -0.0003

Data Index: 626811 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1170796 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0449. Min Act: -0.0003

Data Index: 884207 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0436. Min Act: -0.0003

Data Index: 505113 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0419. Min Act: -0.0003

Data Index: 846732 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0405. Min Act: -0.0003

Data Index: 160393 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0438. Min Act: -0.0003

Data Index: 443483 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0405. Min Act: -0.0003

Data Index: 436313 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0407. Min Act: -0.0003

Data Index: 140672 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1259562 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1044094 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0404. Min Act: -0.0003

Data Index: 105583 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0407. Min Act: -0.0003

Data Index: 403868 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0375. Min Act: -0.0002

Data Index: 290871 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0365. Min Act: -0.0003

Data Index: 476723 (C4 (Web Text))

Max Activating Token Index: 716