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

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

Neuron 3694 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: 3.7562. Min Range: -3.7562

Max Act: 3.7562. Min Act: -0.0000

Data Index: 257475 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.5390. Min Act: -0.0000

Data Index: 495858 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.2121. Min Act: -0.0000

Data Index: 165475 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.1721. Min Act: -0.0000

Data Index: 312576 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.1602. Min Act: -0.0000

Data Index: 627827 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 3.7562. Min Range: -3.7562

Max Act: 2.9952. Min Act: -0.0000

Data Index: 765198 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 3.7562. Min Range: -3.7562

Max Act: 2.9656. Min Act: -0.0000

Data Index: 451159 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.0879. Min Act: -0.0000

Data Index: 410746 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.0858. Min Act: -0.0000

Data Index: 513994 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.0748. Min Act: -0.0000

Data Index: 1120383 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.0599. Min Act: -0.0000

Data Index: 1205600 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.0271. Min Act: -0.0000

Data Index: 531598 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 3.7562. Min Range: -3.7562

Max Act: 2.8729. Min Act: -0.0000

Data Index: 1201566 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 3.7562. Min Range: -3.7562

Max Act: 2.8403. Min Act: -0.0000

Data Index: 708246 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 3.7562. Min Range: -3.7562

Max Act: 3.1145. Min Act: -0.0000

Data Index: 373934 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 3.7562. Min Range: -3.7562

Max Act: 2.9545. Min Act: -0.0000

Data Index: 26669 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 3.7562. Min Range: -3.7562

Max Act: 2.9615. Min Act: -0.0000

Data Index: 1260843 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 3.7562. Min Range: -3.7562

Max Act: 2.9431. Min Act: -0.0000

Data Index: 1159975 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 3.7562. Min Range: -3.7562

Max Act: 2.7877. Min Act: -0.0000

Data Index: 705640 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.7562. Min Range: -3.7562

Max Act: 2.9181. Min Act: -0.0000

Data Index: 809685 (C4 (Web Text))

Max Activating Token Index: 685