Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1526 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.6638. Min Act: -0.0000

Data Index: 1454943 (Python Code)

Max Activating Token Index: 547

Text #1

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.4617. Min Act: -0.0000

Data Index: 1505582 (Python Code)

Max Activating Token Index: 534

Text #2

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3916. Min Act: -0.0000

Data Index: 1478128 (Python Code)

Max Activating Token Index: 905

Text #3

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3589. Min Act: -0.0000

Data Index: 1159192 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.4037. Min Act: -0.0000

Data Index: 1452237 (Python Code)

Max Activating Token Index: 514

Text #5

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1569501 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.4308. Min Act: -0.0000

Data Index: 1531400 (Python Code)

Max Activating Token Index: 688

Text #7

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.2951. Min Act: -0.0000

Data Index: 1614716 (Python Code)

Max Activating Token Index: 408

Text #8

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1375846 (Python Code)

Max Activating Token Index: 961

Text #9

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.4979. Min Act: -0.0000

Data Index: 1188205 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.4303. Min Act: -0.0000

Data Index: 1606827 (Python Code)

Max Activating Token Index: 424

Text #11

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1463318 (Python Code)

Max Activating Token Index: 253

Text #12

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1582364 (Python Code)

Max Activating Token Index: 655

Text #13

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3152. Min Act: -0.0000

Data Index: 1612358 (Python Code)

Max Activating Token Index: 738

Text #14

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3401. Min Act: -0.0000

Data Index: 1488773 (Python Code)

Max Activating Token Index: 624

Text #15

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3070. Min Act: -0.0000

Data Index: 1586493 (Python Code)

Max Activating Token Index: 618

Text #16

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3398. Min Act: -0.0000

Data Index: 1518237 (Python Code)

Max Activating Token Index: 258

Text #17

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.2331. Min Act: -0.0000

Data Index: 1558747 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3289. Min Act: -0.0000

Data Index: 1655880 (Python Code)

Max Activating Token Index: 297

Text #19

Max Range: 1.6638. Min Range: -1.6638

Max Act: 1.3615. Min Act: -0.0000

Data Index: 1496834 (Python Code)

Max Activating Token Index: 53