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

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

Neuron 4221 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1853. Min Range: -2.1853

Max Act: 2.1853. Min Act: -0.0000

Data Index: 611661 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.9823. Min Act: -0.0000

Data Index: 62276 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.8074. Min Act: -0.0000

Data Index: 995958 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.8631. Min Act: -0.0000

Data Index: 156374 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1223068 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.7339. Min Act: -0.0000

Data Index: 177697 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.7267. Min Act: -0.0000

Data Index: 867083 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.5684. Min Act: -0.0000

Data Index: 772202 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.6935. Min Act: -0.0000

Data Index: 344284 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.6909. Min Act: -0.0000

Data Index: 1109652 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.6001. Min Act: -0.0000

Data Index: 674829 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1288123 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.5145. Min Act: -0.0000

Data Index: 819292 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.5070. Min Act: -0.0000

Data Index: 605182 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1179168 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.5259. Min Act: -0.0000

Data Index: 693810 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.5149. Min Act: -0.0000

Data Index: 183420 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.4363. Min Act: -0.0000

Data Index: 1289460 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.4742. Min Act: -0.0000

Data Index: 1615958 (Python Code)

Max Activating Token Index: 766

Text #19

Max Range: 2.1853. Min Range: -2.1853

Max Act: 1.3506. Min Act: -0.0000

Data Index: 1338545 (C4 (Web Text))

Max Activating Token Index: 226