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

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

Neuron 5104 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: 0.0741. Min Range: -0.0741

Max Act: 0.0741. Min Act: -0.0000

Data Index: 1117561 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1455820 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1523506 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0491. Min Act: -0.0000

Data Index: 1560191 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0423. Min Act: -0.0000

Data Index: 338815 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0446. Min Act: -0.0000

Data Index: 805071 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0415. Min Act: -0.0000

Data Index: 136114 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0346. Min Act: -0.0000

Data Index: 1491387 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0393. Min Act: -0.0000

Data Index: 1220705 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1573035 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0384. Min Act: -0.0000

Data Index: 491414 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1399537 (Python Code)

Max Activating Token Index: 640

Text #12

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1526490 (Python Code)

Max Activating Token Index: 244

Text #13

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1525565 (Python Code)

Max Activating Token Index: 455

Text #14

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0384. Min Act: -0.0000

Data Index: 280380 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0353. Min Act: -0.0000

Data Index: 1433108 (Python Code)

Max Activating Token Index: 943

Text #16

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0367. Min Act: -0.0000

Data Index: 305747 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0392. Min Act: -0.0000

Data Index: 1565465 (Python Code)

Max Activating Token Index: 493

Text #18

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1393470 (Python Code)

Max Activating Token Index: 667

Text #19

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0384. Min Act: -0.0001

Data Index: 713467 (C4 (Web Text))

Max Activating Token Index: 817