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

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

Neuron 3674 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: 2.5811. Min Range: -2.5811

Max Act: 2.5811. Min Act: -0.0002

Data Index: 1072891 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.5430. Min Act: -0.0002

Data Index: 520118 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.5060. Min Act: -0.0002

Data Index: 722268 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2875. Min Act: -0.0002

Data Index: 303474 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.4002. Min Act: -0.0002

Data Index: 47697 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2983. Min Act: -0.0002

Data Index: 200052 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.3884. Min Act: -0.0002

Data Index: 356461 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.3764. Min Act: -0.0002

Data Index: 555829 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2896. Min Act: -0.0002

Data Index: 1316706 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2604. Min Act: -0.0002

Data Index: 1055742 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2668. Min Act: -0.0002

Data Index: 280205 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2775. Min Act: -0.0002

Data Index: 1336789 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2336. Min Act: -0.0002

Data Index: 1025376 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2576. Min Act: -0.0002

Data Index: 1242301 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2343. Min Act: -0.0002

Data Index: 486989 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.1774. Min Act: -0.0002

Data Index: 819980 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.1862. Min Act: -0.0003

Data Index: 288619 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2387. Min Act: -0.0002

Data Index: 687175 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2479. Min Act: -0.0002

Data Index: 833880 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 2.5811. Min Range: -2.5811

Max Act: 2.2271. Min Act: -0.0002

Data Index: 664745 (C4 (Web Text))

Max Activating Token Index: 873