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

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

Neuron 2831 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1600223 (Python Code)

Max Activating Token Index: 596

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1479512 (Python Code)

Max Activating Token Index: 908

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1624200 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1586065 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1501443 (Python Code)

Max Activating Token Index: 940

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1648473 (Python Code)

Max Activating Token Index: 226

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1636352 (Python Code)

Max Activating Token Index: 807

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1441345 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1583946 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1596682 (Python Code)

Max Activating Token Index: 498

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1422119 (Python Code)

Max Activating Token Index: 778

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1481249 (Python Code)

Max Activating Token Index: 229

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1495753 (Python Code)

Max Activating Token Index: 859

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1546847 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1378906 (Python Code)

Max Activating Token Index: 163

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1619487 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1532760 (Python Code)

Max Activating Token Index: 847

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1654374 (Python Code)

Max Activating Token Index: 288

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1519358 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0373. Min Act: -0.0002

Data Index: 1495251 (Python Code)

Max Activating Token Index: 224