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

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

Neuron 1521 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: 0.4720. Min Range: -0.4720

Max Act: 0.4568. Min Act: -0.0001

Data Index: 473426 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4476. Min Act: -0.0000

Data Index: 559154 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4720. Min Act: -0.0001

Data Index: 1495648 (Python Code)

Max Activating Token Index: 321

Text #3

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4343. Min Act: -0.0000

Data Index: 592651 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4418. Min Act: -0.0000

Data Index: 939297 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4000. Min Act: -0.0000

Data Index: 1143891 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4438. Min Act: -0.0000

Data Index: 1485056 (Python Code)

Max Activating Token Index: 225

Text #7

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4208. Min Act: -0.0000

Data Index: 903363 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1199515 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1380125 (Python Code)

Max Activating Token Index: 611

Text #10

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4002. Min Act: -0.0000

Data Index: 139715 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3855. Min Act: -0.0000

Data Index: 954320 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4008. Min Act: -0.0000

Data Index: 677719 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4077. Min Act: -0.0001

Data Index: 1298591 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1300691 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.4072. Min Act: -0.0001

Data Index: 850420 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1141331 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3700. Min Act: -0.0000

Data Index: 169651 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3995. Min Act: -0.0000

Data Index: 191766 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.4720. Min Range: -0.4720

Max Act: 0.3616. Min Act: -0.0001

Data Index: 599915 (C4 (Web Text))

Max Activating Token Index: 726