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

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

Neuron 2589 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8878. Min Range: -3.8878

Max Act: 3.8878. Min Act: -0.0001

Data Index: 752227 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 3.8878. Min Range: -3.8878

Max Act: 3.8387. Min Act: -0.0001

Data Index: 706145 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 3.8878. Min Range: -3.8878

Max Act: 3.5736. Min Act: -0.0001

Data Index: 864246 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 3.8878. Min Range: -3.8878

Max Act: 3.3408. Min Act: -0.0001

Data Index: 1307880 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 3.8878. Min Range: -3.8878

Max Act: 3.3046. Min Act: -0.0001

Data Index: 870382 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 3.8878. Min Range: -3.8878

Max Act: 2.8983. Min Act: -0.0001

Data Index: 120415 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 3.8878. Min Range: -3.8878

Max Act: 3.0142. Min Act: -0.0001

Data Index: 275490 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 3.8878. Min Range: -3.8878

Max Act: 3.0003. Min Act: -0.0001

Data Index: 628199 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 3.8878. Min Range: -3.8878

Max Act: 2.9984. Min Act: -0.0001

Data Index: 448785 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 3.8878. Min Range: -3.8878

Max Act: 2.6330. Min Act: -0.0001

Data Index: 611271 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 3.8878. Min Range: -3.8878

Max Act: 2.1322. Min Act: -0.0001

Data Index: 254105 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 3.8878. Min Range: -3.8878

Max Act: 1.9372. Min Act: -0.0001

Data Index: 796691 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 3.8878. Min Range: -3.8878

Max Act: 1.7933. Min Act: -0.0001

Data Index: 33187 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.8878. Min Range: -3.8878

Max Act: 1.8194. Min Act: -0.0001

Data Index: 563595 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 3.8878. Min Range: -3.8878

Max Act: 1.5785. Min Act: -0.0001

Data Index: 643639 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 3.8878. Min Range: -3.8878

Max Act: 1.8647. Min Act: -0.0001

Data Index: 967448 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 3.8878. Min Range: -3.8878

Max Act: 1.7557. Min Act: -0.0001

Data Index: 980895 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 3.8878. Min Range: -3.8878

Max Act: 1.6696. Min Act: -0.0001

Data Index: 464841 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 3.8878. Min Range: -3.8878

Max Act: 1.5576. Min Act: -0.0001

Data Index: 477354 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 3.8878. Min Range: -3.8878

Max Act: 1.6207. Min Act: -0.0001

Data Index: 594379 (C4 (Web Text))

Max Activating Token Index: 144