Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2696 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1236031 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1042959 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1317519 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3654. Min Act: -0.0000

Data Index: 200376 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3637. Min Act: -0.0000

Data Index: 373737 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3128. Min Act: -0.0000

Data Index: 718583 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2982. Min Act: -0.0000

Data Index: 428871 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2672. Min Act: -0.0000

Data Index: 335095 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2903. Min Act: -0.0000

Data Index: 160355 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1483148 (Python Code)

Max Activating Token Index: 587

Text #10

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1174078 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.3031. Min Act: -0.0000

Data Index: 618580 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1032419 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2825. Min Act: -0.0000

Data Index: 393517 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2799. Min Act: -0.0000

Data Index: 502203 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1097507 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2772. Min Act: -0.0000

Data Index: 656783 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2868. Min Act: -0.0000

Data Index: 208087 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2626. Min Act: -0.0000

Data Index: 886729 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.4524. Min Range: -0.4524

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1063857 (C4 (Web Text))

Max Activating Token Index: 460