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

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

Neuron 3555 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.3604. Min Act: -0.0002

Data Index: 1502566 (Python Code)

Max Activating Token Index: 768

Text #1

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.3629. Min Act: -0.0002

Data Index: 1476721 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.3621. Min Act: -0.0002

Data Index: 1579746 (Python Code)

Max Activating Token Index: 238

Text #3

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.3380. Min Act: -0.0002

Data Index: 1477584 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.3166. Min Act: -0.0002

Data Index: 1594338 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.3025. Min Act: -0.0002

Data Index: 1449135 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2998. Min Act: -0.0002

Data Index: 1455154 (Python Code)

Max Activating Token Index: 739

Text #7

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2709. Min Act: -0.0002

Data Index: 1565041 (Python Code)

Max Activating Token Index: 701

Text #8

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2652. Min Act: -0.0002

Data Index: 1638825 (Python Code)

Max Activating Token Index: 201

Text #9

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2634. Min Act: -0.0002

Data Index: 1652266 (Python Code)

Max Activating Token Index: 867

Text #10

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2645. Min Act: -0.0002

Data Index: 1378412 (Python Code)

Max Activating Token Index: 43

Text #11

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2765. Min Act: -0.0002

Data Index: 1411153 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2609. Min Act: -0.0002

Data Index: 1520410 (Python Code)

Max Activating Token Index: 99

Text #13

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2505. Min Act: -0.0002

Data Index: 1398464 (Python Code)

Max Activating Token Index: 658

Text #14

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2534. Min Act: -0.0002

Data Index: 1629826 (Python Code)

Max Activating Token Index: 699

Text #15

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2666. Min Act: -0.0002

Data Index: 1374567 (Python Code)

Max Activating Token Index: 583

Text #16

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2410. Min Act: -0.0002

Data Index: 1386076 (Python Code)

Max Activating Token Index: 887

Text #17

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2414. Min Act: -0.0002

Data Index: 1415343 (Python Code)

Max Activating Token Index: 675

Text #18

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2395. Min Act: -0.0002

Data Index: 1469333 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 1.3629. Min Range: -1.3629

Max Act: 1.2353. Min Act: -0.0002

Data Index: 1639608 (Python Code)

Max Activating Token Index: 507