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

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

Neuron 1013 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8262. Min Range: -2.8262

Max Act: 2.8262. Min Act: -0.0000

Data Index: 978535 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 2.8262. Min Range: -2.8262

Max Act: 2.2192. Min Act: -0.0000

Data Index: 1629726 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.9571. Min Act: -0.0000

Data Index: 726968 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.9800. Min Act: -0.0000

Data Index: 1647760 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.7437. Min Act: -0.0000

Data Index: 958985 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.9402. Min Act: -0.0000

Data Index: 1202254 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.2543. Min Act: -0.0000

Data Index: 779960 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.7328. Min Act: -0.0000

Data Index: 941725 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.5007. Min Act: -0.0000

Data Index: 220011 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1369775 (Python Code)

Max Activating Token Index: 244

Text #10

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1434323 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.3713. Min Act: -0.0000

Data Index: 1652954 (Python Code)

Max Activating Token Index: 398

Text #12

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.3042. Min Act: -0.0000

Data Index: 1631237 (Python Code)

Max Activating Token Index: 995

Text #13

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.4159. Min Act: -0.0000

Data Index: 73808 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.2533. Min Act: -0.0000

Data Index: 1064598 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.3210. Min Act: -0.0000

Data Index: 561018 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1383378 (Python Code)

Max Activating Token Index: 64

Text #17

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1288190 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 2.8262. Min Range: -2.8262

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1098868 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 2.8262. Min Range: -2.8262

Max Act: 1.3310. Min Act: -0.0000

Data Index: 1655898 (Python Code)

Max Activating Token Index: 96