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

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

Neuron 3096 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1717. Min Act: -0.0001

Data Index: 1622552 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1479932 (Python Code)

Max Activating Token Index: 875

Text #2

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1394037 (Python Code)

Max Activating Token Index: 814

Text #3

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1443. Min Act: -0.0001

Data Index: 1515650 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1514909 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1464. Min Act: -0.0000

Data Index: 684963 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1538397 (Python Code)

Max Activating Token Index: 253

Text #7

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1461. Min Act: -0.0000

Data Index: 1383241 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1591890 (Python Code)

Max Activating Token Index: 368

Text #9

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1497734 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1417093 (Python Code)

Max Activating Token Index: 510

Text #11

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1349. Min Act: -0.0001

Data Index: 977396 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1555512 (Python Code)

Max Activating Token Index: 717

Text #13

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1539746 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1498675 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1421. Min Act: -0.0001

Data Index: 1600044 (Python Code)

Max Activating Token Index: 684

Text #16

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1356. Min Act: -0.0001

Data Index: 155558 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1532946 (Python Code)

Max Activating Token Index: 844

Text #18

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1308. Min Act: -0.0001

Data Index: 1451817 (Python Code)

Max Activating Token Index: 669

Text #19

Max Range: 0.1717. Min Range: -0.1717

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1602124 (Python Code)

Max Activating Token Index: 260