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

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

Neuron 1066 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1417732 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7204. Min Act: -0.0000

Data Index: 719489 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1417292 (Python Code)

Max Activating Token Index: 29

Text #3

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1420765 (Python Code)

Max Activating Token Index: 89

Text #4

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1634636 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1627174 (Python Code)

Max Activating Token Index: 605

Text #6

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1459653 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1391857 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1362850 (Python Code)

Max Activating Token Index: 611

Text #9

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1461491 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1363239 (Python Code)

Max Activating Token Index: 862

Text #11

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5347. Min Act: -0.0000

Data Index: 1589512 (Python Code)

Max Activating Token Index: 425

Text #12

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1592340 (Python Code)

Max Activating Token Index: 317

Text #13

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1492530 (Python Code)

Max Activating Token Index: 507

Text #14

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1582285 (Python Code)

Max Activating Token Index: 116

Text #15

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1395110 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1610431 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.5035. Min Act: -0.0000

Data Index: 15671 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1557013 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 0.7466. Min Range: -0.7466

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1602314 (Python Code)

Max Activating Token Index: 883