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

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

Neuron 2717 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: 1.6593. Min Range: -1.6593

Max Act: 1.6593. Min Act: -0.0002

Data Index: 606600 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.6405. Min Act: -0.0002

Data Index: 1183189 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.6390. Min Act: -0.0002

Data Index: 1339976 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.6025. Min Act: -0.0002

Data Index: 1268865 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.6208. Min Act: -0.0002

Data Index: 865425 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.6035. Min Act: -0.0002

Data Index: 726242 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.6022. Min Act: -0.0002

Data Index: 907084 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.6051. Min Act: -0.0002

Data Index: 385887 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5837. Min Act: -0.0002

Data Index: 344668 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5378. Min Act: -0.0002

Data Index: 394062 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5377. Min Act: -0.0002

Data Index: 243496 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5576. Min Act: -0.0002

Data Index: 538449 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5544. Min Act: -0.0003

Data Index: 1325425 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5376. Min Act: -0.0002

Data Index: 762953 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5188. Min Act: -0.0002

Data Index: 345393 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5267. Min Act: -0.0002

Data Index: 50416 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5165. Min Act: -0.0002

Data Index: 865636 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.4852. Min Act: -0.0002

Data Index: 590323 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.5161. Min Act: -0.0002

Data Index: 392425 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 1.6593. Min Range: -1.6593

Max Act: 1.4834. Min Act: -0.0002

Data Index: 233664 (C4 (Web Text))

Max Activating Token Index: 71