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

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

Neuron 5393 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: 0.5270. Min Range: -0.5270

Max Act: 0.5263. Min Act: -0.0002

Data Index: 1121810 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5263. Min Act: -0.0002

Data Index: 378453 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5259. Min Act: -0.0002

Data Index: 353529 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5270. Min Act: -0.0002

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5189. Min Act: -0.0002

Data Index: 57479 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5158. Min Act: -0.0002

Data Index: 97316 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5034. Min Act: -0.0002

Data Index: 485154 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5116. Min Act: -0.0002

Data Index: 534991 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.5076. Min Act: -0.0002

Data Index: 160606 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4993. Min Act: -0.0002

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4887. Min Act: -0.0002

Data Index: 1185911 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4761. Min Act: -0.0002

Data Index: 607335 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4752. Min Act: -0.0002

Data Index: 880216 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4731. Min Act: -0.0002

Data Index: 939170 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4693. Min Act: -0.0002

Data Index: 417518 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4658. Min Act: -0.0002

Data Index: 1197325 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4755. Min Act: -0.0002

Data Index: 630943 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4753. Min Act: -0.0002

Data Index: 881547 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4643. Min Act: -0.0003

Data Index: 144027 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.5270. Min Range: -0.5270

Max Act: 0.4616. Min Act: -0.0002

Data Index: 459483 (C4 (Web Text))

Max Activating Token Index: 216