Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1106 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1880. Min Act: -0.0001

Data Index: 79537 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1738. Min Act: -0.0001

Data Index: 613245 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1014135 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1001228 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1521. Min Act: -0.0001

Data Index: 687968 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1009956 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1507. Min Act: -0.0001

Data Index: 368965 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1440. Min Act: -0.0001

Data Index: 41138 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1437. Min Act: -0.0001

Data Index: 801119 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1428. Min Act: -0.0001

Data Index: 845136 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1322064 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1370. Min Act: -0.0001

Data Index: 600838 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1458. Min Act: -0.0001

Data Index: 603189 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1411. Min Act: -0.0001

Data Index: 637658 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1304. Min Act: -0.0001

Data Index: 114256 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1201928 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1342. Min Act: -0.0001

Data Index: 972688 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1226. Min Act: -0.0001

Data Index: 1284676 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1088282 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.1880. Min Range: -0.1880

Max Act: 0.1240. Min Act: -0.0001

Data Index: 247195 (C4 (Web Text))

Max Activating Token Index: 27