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

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

Neuron 5420 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7478. Min Range: -2.7478

Max Act: 2.7478. Min Act: -0.0000

Data Index: 136385 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.7284. Min Act: -0.0000

Data Index: 183819 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.7071. Min Act: -0.0000

Data Index: 1001054 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.7947. Min Act: -0.0000

Data Index: 1208325 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.8640. Min Act: -0.0000

Data Index: 1273888 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.6001. Min Act: -0.0000

Data Index: 35852 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.4102. Min Act: -0.0000

Data Index: 519222 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.5566. Min Act: -0.0000

Data Index: 1141743 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.3953. Min Act: -0.0000

Data Index: 226653 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.4703. Min Act: -0.0000

Data Index: 602684 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.3920. Min Act: -0.0000

Data Index: 859567 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.2936. Min Act: -0.0000

Data Index: 150704 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.2067. Min Act: -0.0000

Data Index: 780017 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.3529. Min Act: -0.0000

Data Index: 892846 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.2662. Min Act: -0.0000

Data Index: 291615 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.1924. Min Act: -0.0000

Data Index: 795008 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.1918. Min Act: -0.0000

Data Index: 919928 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.1650. Min Act: -0.0000

Data Index: 14464 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.2377. Min Act: -0.0000

Data Index: 803643 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 2.7478. Min Range: -2.7478

Max Act: 1.1547. Min Act: -0.0000

Data Index: 1051438 (C4 (Web Text))

Max Activating Token Index: 1022