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

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

Neuron 4306 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7437. Min Range: -3.7437

Max Act: 3.6342. Min Act: -0.0000

Data Index: 837246 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 3.7437. Min Range: -3.7437

Max Act: 3.7437. Min Act: -0.0000

Data Index: 372010 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 3.7437. Min Range: -3.7437

Max Act: 3.4285. Min Act: -0.0000

Data Index: 141551 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 3.7437. Min Range: -3.7437

Max Act: 3.1248. Min Act: -0.0000

Data Index: 757715 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.9677. Min Act: -0.0000

Data Index: 879756 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 3.7437. Min Range: -3.7437

Max Act: 3.1076. Min Act: -0.0000

Data Index: 1064285 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.7826. Min Act: -0.0000

Data Index: 180312 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.9129. Min Act: -0.0000

Data Index: 540734 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.8686. Min Act: -0.0000

Data Index: 54893 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.8146. Min Act: -0.0000

Data Index: 644953 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.8281. Min Act: -0.0000

Data Index: 481518 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.7376. Min Act: -0.0000

Data Index: 874693 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.2768. Min Act: -0.0000

Data Index: 861230 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.5360. Min Act: -0.0000

Data Index: 1044951 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.5361. Min Act: -0.0000

Data Index: 296031 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.6562. Min Act: -0.0000

Data Index: 290050 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.6586. Min Act: -0.0000

Data Index: 148867 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.7733. Min Act: -0.0000

Data Index: 495998 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.7640. Min Act: -0.0000

Data Index: 498737 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 3.7437. Min Range: -3.7437

Max Act: 2.6281. Min Act: -0.0000

Data Index: 1310626 (C4 (Web Text))

Max Activating Token Index: 28