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

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

Neuron 1914 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: 0.7894. Min Range: -0.7894

Max Act: 0.7855. Min Act: -0.0000

Data Index: 413107 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.7894. Min Act: -0.0000

Data Index: 51297 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.6758. Min Act: -0.0000

Data Index: 817708 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.6271. Min Act: -0.0000

Data Index: 414598 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1282015 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5560. Min Act: -0.0000

Data Index: 1113864 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4698. Min Act: -0.0000

Data Index: 538386 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5022. Min Act: -0.0000

Data Index: 306023 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5163. Min Act: -0.0000

Data Index: 712344 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.5142. Min Act: -0.0000

Data Index: 896715 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4504. Min Act: -0.0000

Data Index: 981637 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4637. Min Act: -0.0000

Data Index: 71688 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1323685 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4849. Min Act: -0.0000

Data Index: 139593 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4470. Min Act: -0.0000

Data Index: 850350 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4383. Min Act: -0.0000

Data Index: 95716 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1202030 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4440. Min Act: -0.0000

Data Index: 388016 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4343. Min Act: -0.0000

Data Index: 966751 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.7894. Min Range: -0.7894

Max Act: 0.4369. Min Act: -0.0000

Data Index: 583235 (C4 (Web Text))

Max Activating Token Index: 790