Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2912 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0001

Data Index: 538036 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1663. Min Act: -0.0001

Data Index: 30123 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1652. Min Act: -0.0001

Data Index: 927123 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1179358 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1210123 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1592. Min Act: -0.0001

Data Index: 977750 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1557. Min Act: -0.0001

Data Index: 593840 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1504. Min Act: -0.0001

Data Index: 399498 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1496. Min Act: -0.0001

Data Index: 865874 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1488. Min Act: -0.0001

Data Index: 828375 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1460. Min Act: -0.0001

Data Index: 284488 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1394. Min Act: -0.0001

Data Index: 57330 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1300. Min Act: -0.0001

Data Index: 485019 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1269. Min Act: -0.0001

Data Index: 787557 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1533. Min Act: -0.0001

Data Index: 457402 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1414. Min Act: -0.0001

Data Index: 20469 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1514. Min Act: -0.0001

Data Index: 904866 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1346. Min Act: -0.0001

Data Index: 734675 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1338. Min Act: -0.0001

Data Index: 559569 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1242. Min Act: -0.0001

Data Index: 887667 (C4 (Web Text))

Max Activating Token Index: 561