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

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

Neuron 1963 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.4177. Min Act: -0.0001

Data Index: 1603922 (Python Code)

Max Activating Token Index: 481

Text #1

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2075. Min Act: -0.0001

Data Index: 1384138 (Python Code)

Max Activating Token Index: 787

Text #2

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3397. Min Act: -0.0000

Data Index: 632597 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.2460. Min Act: -0.0000

Data Index: 444069 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1367. Min Act: -0.0000

Data Index: 322511 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.3700. Min Act: -0.0000

Data Index: 1070813 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1058. Min Act: -0.0000

Data Index: 257113 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1767. Min Act: -0.0001

Data Index: 1434123 (Python Code)

Max Activating Token Index: 840

Text #8

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0273. Min Act: -0.0000

Data Index: 1368153 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1251. Min Act: -0.0000

Data Index: 1470704 (Python Code)

Max Activating Token Index: 837

Text #10

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0617. Min Act: -0.0000

Data Index: 832034 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0187. Min Act: -0.0001

Data Index: 1212732 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1476404 (Python Code)

Max Activating Token Index: 761

Text #13

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1417372 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0434. Min Act: -0.0001

Data Index: 1551399 (Python Code)

Max Activating Token Index: 184

Text #15

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1422375 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0039. Min Act: -0.0000

Data Index: 254070 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1433795 (Python Code)

Max Activating Token Index: 244

Text #18

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1574644 (Python Code)

Max Activating Token Index: 710

Text #19

Max Range: 1.4177. Min Range: -1.4177

Max Act: 1.0167. Min Act: -0.0000

Data Index: 639572 (C4 (Web Text))

Max Activating Token Index: 977