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

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

Neuron 4002 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.7180. Min Act: -0.0002

Data Index: 344318 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5374. Min Act: -0.0002

Data Index: 332348 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5134. Min Act: -0.0002

Data Index: 238873 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5813. Min Act: -0.0002

Data Index: 147342 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5366. Min Act: -0.0002

Data Index: 658100 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5610. Min Act: -0.0002

Data Index: 302649 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5497. Min Act: -0.0002

Data Index: 307891 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4750. Min Act: -0.0002

Data Index: 324824 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4869. Min Act: -0.0003

Data Index: 1007063 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4820. Min Act: -0.0002

Data Index: 986181 (C4 (Web Text))

Max Activating Token Index: 436

Text #10

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4885. Min Act: -0.0002

Data Index: 1190457 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4771. Min Act: -0.0002

Data Index: 123027 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.5053. Min Act: -0.0002

Data Index: 113587 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4566. Min Act: -0.0002

Data Index: 748218 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4316. Min Act: -0.0002

Data Index: 448957 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4624. Min Act: -0.0002

Data Index: 1245587 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4146. Min Act: -0.0002

Data Index: 863177 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4567. Min Act: -0.0002

Data Index: 54519 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4494. Min Act: -0.0002

Data Index: 620758 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 1.7180. Min Range: -1.7180

Max Act: 1.4563. Min Act: -0.0002

Data Index: 492626 (C4 (Web Text))

Max Activating Token Index: 833