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

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

Neuron 3107 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.2420. Min Act: -0.0000

Data Index: 524151 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9824. Min Act: -0.0000

Data Index: 498511 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0385. Min Act: -0.0000

Data Index: 736 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0723. Min Act: -0.0000

Data Index: 826717 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0524. Min Act: -0.0000

Data Index: 699616 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9901. Min Act: -0.0000

Data Index: 270439 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1050896 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 1.2420. Min Range: -1.2420

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1171423 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1164197 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9672. Min Act: -0.0000

Data Index: 986472 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1163292 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9770. Min Act: -0.0000

Data Index: 649148 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9432. Min Act: -0.0000

Data Index: 662260 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9670. Min Act: -0.0000

Data Index: 484133 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9627. Min Act: -0.0000

Data Index: 463674 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9586. Min Act: -0.0000

Data Index: 832927 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9283. Min Act: -0.0000

Data Index: 728147 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.8959. Min Act: -0.0000

Data Index: 995324 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.8930. Min Act: -0.0000

Data Index: 537850 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 1.2420. Min Range: -1.2420

Max Act: 0.9428. Min Act: -0.0000

Data Index: 909484 (C4 (Web Text))

Max Activating Token Index: 475