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

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

Neuron 250 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.4382. Min Act: -0.0001

Data Index: 1420978 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3920. Min Act: -0.0001

Data Index: 1533514 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.4236. Min Act: -0.0001

Data Index: 1450090 (Python Code)

Max Activating Token Index: 844

Text #3

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1633212 (Python Code)

Max Activating Token Index: 241

Text #4

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3685. Min Act: -0.0001

Data Index: 1564164 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3808. Min Act: -0.0001

Data Index: 1555506 (Python Code)

Max Activating Token Index: 163

Text #6

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1633101 (Python Code)

Max Activating Token Index: 876

Text #7

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3677. Min Act: -0.0001

Data Index: 1494663 (Python Code)

Max Activating Token Index: 117

Text #8

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3680. Min Act: -0.0001

Data Index: 1470699 (Python Code)

Max Activating Token Index: 661

Text #9

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3453. Min Act: -0.0001

Data Index: 1461772 (Python Code)

Max Activating Token Index: 454

Text #10

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3710. Min Act: -0.0001

Data Index: 1544867 (Python Code)

Max Activating Token Index: 517

Text #11

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3479. Min Act: -0.0001

Data Index: 1608202 (Python Code)

Max Activating Token Index: 905

Text #12

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3512. Min Act: -0.0001

Data Index: 1652758 (Python Code)

Max Activating Token Index: 422

Text #13

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3266. Min Act: -0.0001

Data Index: 1530698 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3493. Min Act: -0.0001

Data Index: 1483068 (Python Code)

Max Activating Token Index: 665

Text #15

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3331. Min Act: -0.0001

Data Index: 1430738 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3566. Min Act: -0.0001

Data Index: 1592798 (Python Code)

Max Activating Token Index: 243

Text #17

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1616012 (Python Code)

Max Activating Token Index: 519

Text #18

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1499304 (Python Code)

Max Activating Token Index: 632

Text #19

Max Range: 0.4382. Min Range: -0.4382

Max Act: 0.3445. Min Act: -0.0001

Data Index: 1497365 (Python Code)

Max Activating Token Index: 611