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

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

Neuron 4175 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1603893 (Python Code)

Max Activating Token Index: 643

Text #1

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1754. Min Act: -0.0000

Data Index: 1465677 (Python Code)

Max Activating Token Index: 311

Text #2

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1519562 (Python Code)

Max Activating Token Index: 999

Text #3

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1555327 (Python Code)

Max Activating Token Index: 407

Text #4

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1568773 (Python Code)

Max Activating Token Index: 827

Text #5

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1656031 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1518544 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1600766 (Python Code)

Max Activating Token Index: 438

Text #8

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1470110 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1619925 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1432. Min Act: -0.0000

Data Index: 295 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1375. Min Act: -0.0000

Data Index: 934145 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1404722 (Python Code)

Max Activating Token Index: 531

Text #13

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1508818 (Python Code)

Max Activating Token Index: 607

Text #14

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1367551 (Python Code)

Max Activating Token Index: 662

Text #15

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1377. Min Act: -0.0000

Data Index: 1423147 (Python Code)

Max Activating Token Index: 393

Text #16

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1608964 (Python Code)

Max Activating Token Index: 267

Text #17

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1380. Min Act: -0.0000

Data Index: 723657 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1615122 (Python Code)

Max Activating Token Index: 800

Text #19

Max Range: 0.2067. Min Range: -0.2067

Max Act: 0.1306. Min Act: -0.0000

Data Index: 625361 (C4 (Web Text))

Max Activating Token Index: 124