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

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

Neuron 1994 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6978. Min Act: -0.0001

Data Index: 1193493 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6558. Min Act: -0.0001

Data Index: 1136980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6588. Min Act: -0.0001

Data Index: 699237 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6436. Min Act: -0.0001

Data Index: 1346853 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6461. Min Act: -0.0001

Data Index: 881341 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6366. Min Act: -0.0001

Data Index: 897046 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6469. Min Act: -0.0001

Data Index: 1190045 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6317. Min Act: -0.0001

Data Index: 793647 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6373. Min Act: -0.0001

Data Index: 996212 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6277. Min Act: -0.0002

Data Index: 452195 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6198. Min Act: -0.0001

Data Index: 371906 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6251. Min Act: -0.0001

Data Index: 561812 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6181. Min Act: -0.0001

Data Index: 370686 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6226. Min Act: -0.0001

Data Index: 1175661 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6242. Min Act: -0.0001

Data Index: 1092331 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6047. Min Act: -0.0001

Data Index: 1160989 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6227. Min Act: -0.0001

Data Index: 423495 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6163. Min Act: -0.0002

Data Index: 122450 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6124. Min Act: -0.0001

Data Index: 77658 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.6978. Min Range: -0.6978

Max Act: 0.6014. Min Act: -0.0001

Data Index: 979451 (C4 (Web Text))

Max Activating Token Index: 59