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

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

Neuron 2666 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1254825 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1144875 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5135. Min Act: -0.0000

Data Index: 301084 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5371. Min Act: -0.0000

Data Index: 226498 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.5750. Min Act: -0.0000

Data Index: 32036 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4889. Min Act: -0.0000

Data Index: 280132 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4652. Min Act: -0.0000

Data Index: 263675 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4805. Min Act: -0.0000

Data Index: 955566 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4708. Min Act: -0.0000

Data Index: 542478 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1022855 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1028007 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4488. Min Act: -0.0000

Data Index: 248709 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4450. Min Act: -0.0000

Data Index: 204472 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4353. Min Act: -0.0000

Data Index: 565889 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4598. Min Act: -0.0000

Data Index: 591959 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4067. Min Act: -0.0000

Data Index: 505347 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4313. Min Act: -0.0000

Data Index: 496065 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4141. Min Act: -0.0000

Data Index: 342468 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4240. Min Act: -0.0000

Data Index: 978943 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.5789. Min Range: -0.5789

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1215016 (C4 (Web Text))

Max Activating Token Index: 796