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

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

Neuron 1356 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5750. Min Act: -0.0000

Data Index: 599781 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5445. Min Act: -0.0000

Data Index: 795189 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4769. Min Act: -0.0000

Data Index: 290344 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5247. Min Act: -0.0000

Data Index: 88036 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4718. Min Act: -0.0000

Data Index: 714147 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5178. Min Act: -0.0000

Data Index: 192177 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4912. Min Act: -0.0000

Data Index: 50414 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4517. Min Act: -0.0000

Data Index: 267157 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4939. Min Act: -0.0000

Data Index: 656281 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1038275 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4191. Min Act: -0.0000

Data Index: 341751 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4466. Min Act: -0.0000

Data Index: 911415 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4891. Min Act: -0.0000

Data Index: 826820 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4888. Min Act: -0.0000

Data Index: 224229 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4386. Min Act: -0.0000

Data Index: 287826 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1251746 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1119850 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4722. Min Act: -0.0000

Data Index: 606055 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4291. Min Act: -0.0000

Data Index: 979300 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.5750. Min Range: -0.5750

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1212478 (C4 (Web Text))

Max Activating Token Index: 710