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

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

Neuron 3792 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: 1.2875. Min Range: -1.2875

Max Act: 1.2875. Min Act: -0.0003

Data Index: 1039106 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1902. Min Act: -0.0002

Data Index: 1060735 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1537. Min Act: -0.0002

Data Index: 1243912 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1661. Min Act: -0.0002

Data Index: 188962 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1315. Min Act: -0.0002

Data Index: 1265179 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1338. Min Act: -0.0002

Data Index: 1348329 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1516. Min Act: -0.0002

Data Index: 415583 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1377. Min Act: -0.0002

Data Index: 476712 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1266. Min Act: -0.0002

Data Index: 1015601 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1067. Min Act: -0.0002

Data Index: 448685 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1005. Min Act: -0.0002

Data Index: 1118904 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1067. Min Act: -0.0002

Data Index: 1083113 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.1000. Min Act: -0.0002

Data Index: 1042719 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0818. Min Act: -0.0002

Data Index: 1075051 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0771. Min Act: -0.0002

Data Index: 1255460 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0944. Min Act: -0.0002

Data Index: 433810 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0728. Min Act: -0.0003

Data Index: 1248241 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0905. Min Act: -0.0002

Data Index: 299164 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0774. Min Act: -0.0002

Data Index: 1144251 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 1.2875. Min Range: -1.2875

Max Act: 1.0679. Min Act: -0.0002

Data Index: 20085 (C4 (Web Text))

Max Activating Token Index: 719