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

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

Neuron 731 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4879. Min Act: -0.0002

Data Index: 1351711 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4881. Min Act: -0.0002

Data Index: 1275697 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4748. Min Act: -0.0002

Data Index: 321772 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4801. Min Act: -0.0002

Data Index: 665022 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4737. Min Act: -0.0002

Data Index: 1308312 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4671. Min Act: -0.0002

Data Index: 696893 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4619. Min Act: -0.0002

Data Index: 1131845 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4734. Min Act: -0.0002

Data Index: 420385 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4723. Min Act: -0.0002

Data Index: 327714 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4540. Min Act: -0.0002

Data Index: 692909 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4588. Min Act: -0.0002

Data Index: 834709 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4638. Min Act: -0.0002

Data Index: 1103669 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4638. Min Act: -0.0002

Data Index: 587106 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4638. Min Act: -0.0002

Data Index: 117245 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4638. Min Act: -0.0002

Data Index: 299613 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4638. Min Act: -0.0002

Data Index: 617659 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4638. Min Act: -0.0002

Data Index: 963871 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4500. Min Act: -0.0003

Data Index: 136568 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4610. Min Act: -0.0002

Data Index: 275565 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.4881. Min Range: -0.4881

Max Act: 0.4488. Min Act: -0.0002

Data Index: 653387 (C4 (Web Text))

Max Activating Token Index: 151