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

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

Neuron 687 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: 0.5474. Min Range: -0.5474

Max Act: 0.5474. Min Act: -0.0002

Data Index: 271359 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5461. Min Act: -0.0002

Data Index: 972324 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5402. Min Act: -0.0002

Data Index: 967520 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5373. Min Act: -0.0002

Data Index: 253405 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5323. Min Act: -0.0002

Data Index: 908052 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5162. Min Act: -0.0002

Data Index: 1054368 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5172. Min Act: -0.0002

Data Index: 1162218 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5087. Min Act: -0.0002

Data Index: 1236942 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5074. Min Act: -0.0002

Data Index: 71260 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5015. Min Act: -0.0002

Data Index: 189999 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4868. Min Act: -0.0002

Data Index: 36634 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4877. Min Act: -0.0002

Data Index: 240523 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5001. Min Act: -0.0002

Data Index: 1332510 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4866. Min Act: -0.0003

Data Index: 193865 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4792. Min Act: -0.0002

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4758. Min Act: -0.0002

Data Index: 982918 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4752. Min Act: -0.0002

Data Index: 1289828 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4694. Min Act: -0.0002

Data Index: 158677 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4724. Min Act: -0.0002

Data Index: 204206 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4669. Min Act: -0.0002

Data Index: 1512785 (Python Code)

Max Activating Token Index: 771