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

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

Neuron 31 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4989. Min Range: -2.4989

Max Act: 2.4989. Min Act: -0.0000

Data Index: 699663 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 2.4989. Min Range: -2.4989

Max Act: 2.4793. Min Act: -0.0000

Data Index: 662172 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 2.4989. Min Range: -2.4989

Max Act: 2.1053. Min Act: -0.0000

Data Index: 918536 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 2.4989. Min Range: -2.4989

Max Act: 2.0540. Min Act: -0.0000

Data Index: 1268968 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 2.4989. Min Range: -2.4989

Max Act: 2.0368. Min Act: -0.0000

Data Index: 593383 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 2.4989. Min Range: -2.4989

Max Act: 2.0660. Min Act: -0.0000

Data Index: 676395 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.8989. Min Act: -0.0000

Data Index: 155252 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.7799. Min Act: -0.0000

Data Index: 262600 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.7852. Min Act: -0.0000

Data Index: 743876 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.6468. Min Act: -0.0000

Data Index: 1142033 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.7823. Min Act: -0.0000

Data Index: 803421 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.7666. Min Act: -0.0000

Data Index: 55459 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.5742. Min Act: -0.0000

Data Index: 30560 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.6661. Min Act: -0.0000

Data Index: 568968 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.5576. Min Act: -0.0000

Data Index: 129153 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.7089. Min Act: -0.0000

Data Index: 330288 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.5024. Min Act: -0.0000

Data Index: 118727 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.5777. Min Act: -0.0000

Data Index: 55392 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.6475. Min Act: -0.0000

Data Index: 997137 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 2.4989. Min Range: -2.4989

Max Act: 1.5556. Min Act: -0.0000

Data Index: 665350 (C4 (Web Text))

Max Activating Token Index: 528