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

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

Neuron 2441 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0002

Data Index: 514721 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1599085 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1461961 (Python Code)

Max Activating Token Index: 247

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1570395 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1563055 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1536541 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1475321 (Python Code)

Max Activating Token Index: 646

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1541435 (Python Code)

Max Activating Token Index: 229

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1378838 (Python Code)

Max Activating Token Index: 484

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0355. Min Act: -0.0002

Data Index: 1403671 (Python Code)

Max Activating Token Index: 615

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0352. Min Act: -0.0002

Data Index: 1366796 (Python Code)

Max Activating Token Index: 567

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1476638 (Python Code)

Max Activating Token Index: 518

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1640847 (Python Code)

Max Activating Token Index: 129

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1578644 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0350. Min Act: -0.0002

Data Index: 937726 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1431653 (Python Code)

Max Activating Token Index: 616

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1506796 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1548459 (Python Code)

Max Activating Token Index: 410

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1607495 (Python Code)

Max Activating Token Index: 438

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1577912 (Python Code)

Max Activating Token Index: 155