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

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

Neuron 3560 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1863. Min Range: -2.1863

Max Act: 2.1863. Min Act: -0.0000

Data Index: 970970 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 2.1863. Min Range: -2.1863

Max Act: 2.1077. Min Act: -0.0000

Data Index: 1060980 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 2.1863. Min Range: -2.1863

Max Act: 2.1746. Min Act: -0.0000

Data Index: 368991 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.8936. Min Act: -0.0000

Data Index: 285508 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7934. Min Act: -0.0000

Data Index: 978639 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7508. Min Act: -0.0000

Data Index: 830580 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.6159. Min Act: -0.0000

Data Index: 676463 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.5995. Min Act: -0.0000

Data Index: 535919 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.7295. Min Act: -0.0000

Data Index: 1186753 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.6148. Min Act: -0.0000

Data Index: 305575 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.5759. Min Act: -0.0000

Data Index: 117500 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.4799. Min Act: -0.0000

Data Index: 744320 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.5660. Min Act: -0.0000

Data Index: 165875 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.4337. Min Act: -0.0000

Data Index: 738231 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.5567. Min Act: -0.0000

Data Index: 454635 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.5978. Min Act: -0.0000

Data Index: 914566 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.6473. Min Act: -0.0000

Data Index: 832402 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.5457. Min Act: -0.0000

Data Index: 793500 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.5472. Min Act: -0.0000

Data Index: 413965 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 2.1863. Min Range: -2.1863

Max Act: 1.4850. Min Act: -0.0000

Data Index: 1227417 (C4 (Web Text))

Max Activating Token Index: 39