Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1285 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.3182. Min Act: -0.0001

Data Index: 1200651 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.1935. Min Act: -0.0001

Data Index: 794866 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.1468. Min Act: -0.0001

Data Index: 266764 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.1199. Min Act: -0.0001

Data Index: 956994 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.1455. Min Act: -0.0001

Data Index: 526281 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.2546. Min Act: -0.0001

Data Index: 1073067 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.1200. Min Act: -0.0001

Data Index: 614786 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.1218. Min Act: -0.0001

Data Index: 726051 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.1011. Min Act: -0.0001

Data Index: 969463 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.0855. Min Act: -0.0001

Data Index: 1243769 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.0591. Min Act: -0.0001

Data Index: 639374 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 1.3182. Min Range: -1.3182

Max Act: 0.9841. Min Act: -0.0001

Data Index: 650804 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 1.3182. Min Range: -1.3182

Max Act: 0.9750. Min Act: -0.0001

Data Index: 16703 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.0062. Min Act: -0.0001

Data Index: 713332 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 1.3182. Min Range: -1.3182

Max Act: 1.0985. Min Act: -0.0001

Data Index: 1168933 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 1.3182. Min Range: -1.3182

Max Act: 0.9986. Min Act: -0.0001

Data Index: 1351353 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 1.3182. Min Range: -1.3182

Max Act: 0.9850. Min Act: -0.0001

Data Index: 141790 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 1.3182. Min Range: -1.3182

Max Act: 0.9517. Min Act: -0.0001

Data Index: 1001015 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 1.3182. Min Range: -1.3182

Max Act: 0.9313. Min Act: -0.0001

Data Index: 411743 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 1.3182. Min Range: -1.3182

Max Act: 0.9513. Min Act: -0.0001

Data Index: 743126 (C4 (Web Text))

Max Activating Token Index: 22