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

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

Neuron 1407 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.2010. Min Act: -0.0000

Data Index: 715041 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1832. Min Act: -0.0000

Data Index: 143494 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1192292 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1832. Min Act: -0.0000

Data Index: 737243 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1009532 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1597. Min Act: -0.0000

Data Index: 175362 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1531. Min Act: -0.0000

Data Index: 360292 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1431. Min Act: -0.0000

Data Index: 305225 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1435. Min Act: -0.0000

Data Index: 740738 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1433. Min Act: -0.0000

Data Index: 474486 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1474. Min Act: -0.0000

Data Index: 437531 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1373. Min Act: -0.0000

Data Index: 552827 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1330. Min Act: -0.0000

Data Index: 141230 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1357. Min Act: -0.0000

Data Index: 179101 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1354. Min Act: -0.0000

Data Index: 202952 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1339. Min Act: -0.0000

Data Index: 796429 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1263. Min Act: -0.0000

Data Index: 325154 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1241962 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1285. Min Act: -0.0000

Data Index: 869124 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.2010. Min Range: -0.2010

Max Act: 0.1267. Min Act: -0.0000

Data Index: 356098 (C4 (Web Text))

Max Activating Token Index: 674