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

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

Neuron 4192 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6465. Min Range: -3.6465

Max Act: 3.6465. Min Act: -0.0001

Data Index: 1008723 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 3.6465. Min Range: -3.6465

Max Act: 3.2838. Min Act: -0.0001

Data Index: 567690 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 3.6465. Min Range: -3.6465

Max Act: 3.2712. Min Act: -0.0001

Data Index: 381298 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 3.6465. Min Range: -3.6465

Max Act: 3.2397. Min Act: -0.0001

Data Index: 950595 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 3.6465. Min Range: -3.6465

Max Act: 3.0225. Min Act: -0.0001

Data Index: 607318 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 3.6465. Min Range: -3.6465

Max Act: 3.1631. Min Act: -0.0001

Data Index: 199879 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 3.6465. Min Range: -3.6465

Max Act: 3.1146. Min Act: -0.0001

Data Index: 234465 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 3.6465. Min Range: -3.6465

Max Act: 3.0926. Min Act: -0.0001

Data Index: 1065467 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 3.6465. Min Range: -3.6465

Max Act: 3.0809. Min Act: -0.0001

Data Index: 1292138 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.9013. Min Act: -0.0001

Data Index: 373902 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.8567. Min Act: -0.0001

Data Index: 1348413 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.9841. Min Act: -0.0001

Data Index: 454636 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.9891. Min Act: -0.0001

Data Index: 190036 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.9786. Min Act: -0.0001

Data Index: 317382 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.9398. Min Act: -0.0001

Data Index: 439491 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.8743. Min Act: -0.0000

Data Index: 331847 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.8696. Min Act: -0.0001

Data Index: 303700 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.8822. Min Act: -0.0000

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.8626. Min Act: -0.0001

Data Index: 1321150 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 3.6465. Min Range: -3.6465

Max Act: 2.9534. Min Act: -0.0001

Data Index: 813294 (C4 (Web Text))

Max Activating Token Index: 214