Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2938 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.5268. Min Act: -0.0001

Data Index: 499398 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.5344. Min Act: -0.0001

Data Index: 960028 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4892. Min Act: -0.0002

Data Index: 106218 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4698. Min Act: -0.0002

Data Index: 215086 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4606. Min Act: -0.0001

Data Index: 1267101 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.5223. Min Act: -0.0001

Data Index: 897847 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4968. Min Act: -0.0002

Data Index: 243794 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4947. Min Act: -0.0002

Data Index: 241956 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4898. Min Act: -0.0002

Data Index: 7609 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4118. Min Act: -0.0002

Data Index: 456665 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4913. Min Act: -0.0002

Data Index: 271634 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4692. Min Act: -0.0001

Data Index: 1229742 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4884. Min Act: -0.0002

Data Index: 222180 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4516. Min Act: -0.0002

Data Index: 702072 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4298. Min Act: -0.0001

Data Index: 833974 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4269. Min Act: -0.0002

Data Index: 1084582 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4802. Min Act: -0.0001

Data Index: 180088 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4609. Min Act: -0.0001

Data Index: 621658 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.3929. Min Act: -0.0002

Data Index: 1285419 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.5344. Min Range: -0.5344

Max Act: 0.4561. Min Act: -0.0001

Data Index: 324657 (C4 (Web Text))

Max Activating Token Index: 558