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

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

Neuron 2901 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: 0.4604. Min Range: -0.4604

Max Act: 0.4604. Min Act: -0.0000

Data Index: 649014 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1189067 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1820. Min Act: -0.0000

Data Index: 377819 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1766. Min Act: -0.0001

Data Index: 399621 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1823. Min Act: -0.0001

Data Index: 915038 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1640. Min Act: -0.0000

Data Index: 438363 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1323374 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1643. Min Act: -0.0000

Data Index: 606718 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1019842 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1657. Min Act: -0.0001

Data Index: 101115 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1505. Min Act: -0.0001

Data Index: 120345 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1302817 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1508. Min Act: -0.0001

Data Index: 1101742 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1524. Min Act: -0.0001

Data Index: 396245 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1316491 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1059166 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1375. Min Act: -0.0000

Data Index: 782501 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1430. Min Act: -0.0001

Data Index: 185924 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1363. Min Act: -0.0000

Data Index: 977475 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.4604. Min Range: -0.4604

Max Act: 0.1359. Min Act: -0.0000

Data Index: 841381 (C4 (Web Text))

Max Activating Token Index: 20