Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1460 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0603. Min Act: -0.0002

Data Index: 817361 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1621420 (Python Code)

Max Activating Token Index: 299

Text #2

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1388150 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1447494 (Python Code)

Max Activating Token Index: 440

Text #4

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1457606 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1562630 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1556793 (Python Code)

Max Activating Token Index: 137

Text #7

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0434. Min Act: -0.0002

Data Index: 670790 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1595785 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1449469 (Python Code)

Max Activating Token Index: 586

Text #10

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0418. Min Act: -0.0002

Data Index: 642510 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0414. Min Act: -0.0002

Data Index: 75802 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0412. Min Act: -0.0002

Data Index: 552396 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0404. Min Act: -0.0002

Data Index: 531413 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1570357 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0420. Min Act: -0.0002

Data Index: 219794 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1475522 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1491537 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1602606 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 0.0603. Min Range: -0.0603

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1058648 (C4 (Web Text))

Max Activating Token Index: 623