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

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

Neuron 3042 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1051613 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4847. Min Act: -0.0000

Data Index: 864171 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1053335 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5365. Min Act: -0.0000

Data Index: 135313 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4850. Min Act: -0.0000

Data Index: 222300 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5106. Min Act: -0.0000

Data Index: 899635 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.5182. Min Act: -0.0000

Data Index: 524984 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4830. Min Act: -0.0000

Data Index: 744906 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1250391 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4884. Min Act: -0.0000

Data Index: 37576 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4858. Min Act: -0.0000

Data Index: 703862 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4850. Min Act: -0.0000

Data Index: 1162770 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4747. Min Act: -0.0000

Data Index: 435050 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4546. Min Act: -0.0000

Data Index: 37167 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4662. Min Act: -0.0000

Data Index: 878849 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4532. Min Act: -0.0000

Data Index: 214454 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4559. Min Act: -0.0000

Data Index: 721581 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4606. Min Act: -0.0000

Data Index: 482002 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4851. Min Act: -0.0000

Data Index: 820910 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.5696. Min Range: -0.5696

Max Act: 0.4807. Min Act: -0.0000

Data Index: 762620 (C4 (Web Text))

Max Activating Token Index: 489