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

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

Neuron 6131 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: 0.0388. Min Range: -0.0388

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1567440 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1612973 (Python Code)

Max Activating Token Index: 907

Text #2

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1560613 (Python Code)

Max Activating Token Index: 468

Text #3

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0345. Min Act: -0.0002

Data Index: 1511449 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1415226 (Python Code)

Max Activating Token Index: 678

Text #5

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1535328 (Python Code)

Max Activating Token Index: 696

Text #6

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1365478 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0306. Min Act: -0.0002

Data Index: 778442 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1653675 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1374939 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1539503 (Python Code)

Max Activating Token Index: 83

Text #11

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1411719 (Python Code)

Max Activating Token Index: 790

Text #12

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1634672 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1573081 (Python Code)

Max Activating Token Index: 303

Text #14

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1566678 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1434749 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1537886 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1522583 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1581515 (Python Code)

Max Activating Token Index: 480

Text #19

Max Range: 0.0388. Min Range: -0.0388

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1650008 (Python Code)

Max Activating Token Index: 76