Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1811 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.0100. Min Range: -7.0100

Max Act: 7.0100. Min Act: -0.0000

Data Index: 350822 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.7756. Min Act: -0.0000

Data Index: 124378 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.3337. Min Act: -0.0000

Data Index: 799924 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.1700. Min Act: -0.0000

Data Index: 936235 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.0348. Min Act: -0.0000

Data Index: 1080884 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.1291. Min Act: -0.0000

Data Index: 1178290 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.2827. Min Act: -0.0000

Data Index: 656183 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.1119. Min Act: -0.0000

Data Index: 302051 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.0896. Min Act: -0.0000

Data Index: 539662 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.2220. Min Act: -0.0000

Data Index: 1134437 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.2201. Min Act: -0.0000

Data Index: 1063407 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.0861. Min Act: -0.0000

Data Index: 671240 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 7.0100. Min Range: -7.0100

Max Act: 5.9124. Min Act: -0.0000

Data Index: 840652 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 7.0100. Min Range: -7.0100

Max Act: 5.8906. Min Act: -0.0000

Data Index: 1100096 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 7.0100. Min Range: -7.0100

Max Act: 5.7233. Min Act: -0.0000

Data Index: 578466 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.0733. Min Act: -0.0000

Data Index: 47851 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 7.0100. Min Range: -7.0100

Max Act: 5.6459. Min Act: -0.0000

Data Index: 437851 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 7.0100. Min Range: -7.0100

Max Act: 5.6429. Min Act: -0.0000

Data Index: 241250 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 7.0100. Min Range: -7.0100

Max Act: 6.0493. Min Act: -0.0000

Data Index: 1293787 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 7.0100. Min Range: -7.0100

Max Act: 5.9763. Min Act: -0.0000

Data Index: 986852 (C4 (Web Text))

Max Activating Token Index: 130