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

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

Neuron 27 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: 3.0386. Min Range: -3.0386

Max Act: 2.7987. Min Act: -0.0000

Data Index: 372906 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 3.0386. Min Range: -3.0386

Max Act: 3.0386. Min Act: -0.0000

Data Index: 495185 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.7915. Min Act: -0.0000

Data Index: 860306 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.3358. Min Act: -0.0000

Data Index: 533744 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.2657. Min Act: -0.0000

Data Index: 1109141 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.3491. Min Act: -0.0000

Data Index: 1344693 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.0532. Min Act: -0.0000

Data Index: 992240 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.1331. Min Act: -0.0000

Data Index: 695451 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.0482. Min Act: -0.0000

Data Index: 406005 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 3.0386. Min Range: -3.0386

Max Act: 1.9511. Min Act: -0.0000

Data Index: 306367 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.1240. Min Act: -0.0000

Data Index: 546622 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 3.0386. Min Range: -3.0386

Max Act: 1.9775. Min Act: -0.0000

Data Index: 710919 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 3.0386. Min Range: -3.0386

Max Act: 1.9992. Min Act: -0.0000

Data Index: 626415 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.0478. Min Act: -0.0000

Data Index: 641945 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 3.0386. Min Range: -3.0386

Max Act: 2.0413. Min Act: -0.0000

Data Index: 207202 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 3.0386. Min Range: -3.0386

Max Act: 1.7433. Min Act: -0.0000

Data Index: 161408 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 3.0386. Min Range: -3.0386

Max Act: 1.9072. Min Act: -0.0000

Data Index: 1236593 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 3.0386. Min Range: -3.0386

Max Act: 1.8856. Min Act: -0.0000

Data Index: 74728 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 3.0386. Min Range: -3.0386

Max Act: 1.8806. Min Act: -0.0000

Data Index: 124404 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 3.0386. Min Range: -3.0386

Max Act: 1.9063. Min Act: -0.0000

Data Index: 888234 (C4 (Web Text))

Max Activating Token Index: 939