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

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

Neuron 5421 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: 1.6223. Min Range: -1.6223

Max Act: 1.6223. Min Act: -0.0000

Data Index: 1042673 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2043. Min Act: -0.0000

Data Index: 527719 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1833. Min Act: -0.0000

Data Index: 506970 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1010. Min Act: -0.0000

Data Index: 948781 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1067104 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0481. Min Act: -0.0000

Data Index: 672045 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0351. Min Act: -0.0000

Data Index: 826886 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0603. Min Act: -0.0000

Data Index: 261395 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0616. Min Act: -0.0000

Data Index: 853161 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0209. Min Act: -0.0000

Data Index: 67535 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9170. Min Act: -0.0001

Data Index: 714087 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0215. Min Act: -0.0001

Data Index: 771220 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0518. Min Act: -0.0000

Data Index: 428629 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0554. Min Act: -0.0000

Data Index: 972321 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1280842 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.8708. Min Act: -0.0000

Data Index: 1331087 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9565. Min Act: -0.0001

Data Index: 504436 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9427. Min Act: -0.0000

Data Index: 177389 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9756. Min Act: -0.0000

Data Index: 940962 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0055. Min Act: -0.0001

Data Index: 538386 (C4 (Web Text))

Max Activating Token Index: 513