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

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

Neuron 88 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: 4.5779. Min Range: -4.5779

Max Act: 4.5779. Min Act: -0.0001

Data Index: 952913 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.0025. Min Act: -0.0001

Data Index: 1320326 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.1067. Min Act: -0.0000

Data Index: 1150864 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.4016. Min Act: -0.0001

Data Index: 1077368 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.6057. Min Act: -0.0000

Data Index: 1255014 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 4.5779. Min Range: -4.5779

Max Act: 4.0465. Min Act: -0.0001

Data Index: 1047183 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.3716. Min Act: -0.0001

Data Index: 127413 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.8149. Min Act: -0.0001

Data Index: 472863 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.4875. Min Act: -0.0001

Data Index: 404102 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.5766. Min Act: -0.0001

Data Index: 1185332 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.3948. Min Act: -0.0001

Data Index: 955437 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.6353. Min Act: -0.0001

Data Index: 955132 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.4536. Min Act: -0.0001

Data Index: 785034 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.4639. Min Act: -0.0001

Data Index: 1124431 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.5571. Min Act: -0.0000

Data Index: 229920 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.3801. Min Act: -0.0001

Data Index: 725132 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.1866. Min Act: -0.0001

Data Index: 201639 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.3088. Min Act: -0.0000

Data Index: 24540 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.2491. Min Act: -0.0000

Data Index: 1327018 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 4.5779. Min Range: -4.5779

Max Act: 3.1843. Min Act: -0.0001

Data Index: 453351 (C4 (Web Text))

Max Activating Token Index: 968