Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1361 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3340. Min Act: -0.0003

Data Index: 1624306 (Python Code)

Max Activating Token Index: 889

Text #1

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3266. Min Act: -0.0003

Data Index: 1487063 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2603. Min Act: -0.0003

Data Index: 1562887 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.1570. Min Act: -0.0002

Data Index: 544127 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.1181. Min Act: -0.0004

Data Index: 1476733 (Python Code)

Max Activating Token Index: 454

Text #5

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0994. Min Act: -0.0003

Data Index: 1422031 (Python Code)

Max Activating Token Index: 240

Text #6

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0894. Min Act: -0.0003

Data Index: 1453385 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0558. Min Act: -0.0004

Data Index: 78751 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1062480 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1648885 (Python Code)

Max Activating Token Index: 921

Text #10

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0540. Min Act: -0.0003

Data Index: 70434 (C4 (Web Text))

Max Activating Token Index: 259

Text #11

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1072243 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0543. Min Act: -0.0003

Data Index: 295355 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1224704 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0529. Min Act: -0.0002

Data Index: 190093 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1445280 (Python Code)

Max Activating Token Index: 651

Text #16

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0520. Min Act: -0.0003

Data Index: 364133 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0503. Min Act: -0.0003

Data Index: 659318 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0510. Min Act: -0.0003

Data Index: 328115 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.0498. Min Act: -0.0002

Data Index: 265383 (C4 (Web Text))

Max Activating Token Index: 761