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

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

Neuron 1810 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: 4.5478. Min Range: -4.5478

Max Act: 4.5478. Min Act: -0.0000

Data Index: 999423 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.4904. Min Act: -0.0000

Data Index: 640341 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.1575. Min Act: -0.0000

Data Index: 212851 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 4.5478. Min Range: -4.5478

Max Act: 4.1049. Min Act: -0.0000

Data Index: 816834 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.9026. Min Act: -0.0000

Data Index: 965548 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.9289. Min Act: -0.0000

Data Index: 673669 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.6399. Min Act: -0.0000

Data Index: 866329 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.5625. Min Act: -0.0000

Data Index: 151988 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.4774. Min Act: -0.0000

Data Index: 53401 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.2763. Min Act: -0.0000

Data Index: 1213006 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.4264. Min Act: -0.0000

Data Index: 830787 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.1070. Min Act: -0.0000

Data Index: 757611 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.0454. Min Act: -0.0000

Data Index: 98422 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 4.5478. Min Range: -4.5478

Max Act: 2.6433. Min Act: -0.0000

Data Index: 1358597 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.1918. Min Act: -0.0000

Data Index: 1026380 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 4.5478. Min Range: -4.5478

Max Act: 2.8621. Min Act: -0.0000

Data Index: 166405 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 4.5478. Min Range: -4.5478

Max Act: 3.0189. Min Act: -0.0000

Data Index: 1222527 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 4.5478. Min Range: -4.5478

Max Act: 2.8158. Min Act: -0.0000

Data Index: 1104556 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 4.5478. Min Range: -4.5478

Max Act: 2.7266. Min Act: -0.0000

Data Index: 262888 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 4.5478. Min Range: -4.5478

Max Act: 2.3706. Min Act: -0.0000

Data Index: 88664 (C4 (Web Text))

Max Activating Token Index: 796