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

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

Neuron 1894 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: 0.1807. Min Range: -0.1807

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1084978 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1654. Min Act: -0.0001

Data Index: 890709 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1695. Min Act: -0.0000

Data Index: 475306 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1709. Min Act: -0.0000

Data Index: 18574 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1307323 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1536. Min Act: -0.0001

Data Index: 915759 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1563. Min Act: -0.0000

Data Index: 728213 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1507. Min Act: -0.0000

Data Index: 778444 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1498. Min Act: -0.0000

Data Index: 854254 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1550. Min Act: -0.0000

Data Index: 28084 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1512. Min Act: -0.0000

Data Index: 434379 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1498. Min Act: -0.0000

Data Index: 716113 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1339416 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1390. Min Act: -0.0000

Data Index: 133364 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1338010 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1458. Min Act: -0.0000

Data Index: 623822 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1363. Min Act: -0.0000

Data Index: 274062 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1359. Min Act: -0.0000

Data Index: 215246 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1393. Min Act: -0.0000

Data Index: 955810 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1443. Min Act: -0.0000

Data Index: 694284 (C4 (Web Text))

Max Activating Token Index: 32