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

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

Neuron 5077 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: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1535039 (Python Code)

Max Activating Token Index: 795

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0486. Min Act: -0.0001

Data Index: 746714 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1567114 (Python Code)

Max Activating Token Index: 492

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1549134 (Python Code)

Max Activating Token Index: 653

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0429. Min Act: -0.0001

Data Index: 1507035 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1362125 (Python Code)

Max Activating Token Index: 777

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1478583 (Python Code)

Max Activating Token Index: 834

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0399. Min Act: -0.0001

Data Index: 1505637 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0441. Min Act: -0.0001

Data Index: 464497 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0426. Min Act: -0.0001

Data Index: 368600 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0413. Min Act: -0.0001

Data Index: 602352 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1495082 (Python Code)

Max Activating Token Index: 935

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0401. Min Act: -0.0001

Data Index: 806900 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1533793 (Python Code)

Max Activating Token Index: 821

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0368. Min Act: -0.0001

Data Index: 132796 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1633165 (Python Code)

Max Activating Token Index: 687

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0352. Min Act: -0.0001

Data Index: 1511859 (Python Code)

Max Activating Token Index: 1022

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0368. Min Act: -0.0001

Data Index: 1487664 (Python Code)

Max Activating Token Index: 810

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0377. Min Act: -0.0001

Data Index: 910898 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1605047 (Python Code)

Max Activating Token Index: 968