Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1472 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2573. Min Act: -0.0000

Data Index: 861370 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1259929 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1909. Min Act: -0.0000

Data Index: 888420 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1659. Min Act: -0.0001

Data Index: 57659 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1402139 (Python Code)

Max Activating Token Index: 748

Text #5

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1721. Min Act: -0.0000

Data Index: 375415 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1727. Min Act: -0.0001

Data Index: 195380 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1640. Min Act: -0.0000

Data Index: 56560 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1559. Min Act: -0.0001

Data Index: 441531 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1638762 (Python Code)

Max Activating Token Index: 957

Text #10

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1515330 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1691. Min Act: -0.0001

Data Index: 799108 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1548536 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1440023 (Python Code)

Max Activating Token Index: 538

Text #14

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1632318 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1513. Min Act: -0.0000

Data Index: 167791 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1809. Min Act: -0.0001

Data Index: 1554474 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1616. Min Act: -0.0000

Data Index: 828098 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1523. Min Act: -0.0001

Data Index: 677102 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1489607 (Python Code)

Max Activating Token Index: 231