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

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

Neuron 540 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: 0.6388. Min Range: -0.6388

Max Act: 0.6388. Min Act: -0.0002

Data Index: 1046194 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.6192. Min Act: -0.0002

Data Index: 611145 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.6167. Min Act: -0.0002

Data Index: 21447 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.6083. Min Act: -0.0002

Data Index: 598432 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.6079. Min Act: -0.0002

Data Index: 1256150 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5375. Min Act: -0.0002

Data Index: 108412 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5218. Min Act: -0.0002

Data Index: 788222 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5080. Min Act: -0.0002

Data Index: 283424 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5156. Min Act: -0.0002

Data Index: 1075636 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5097. Min Act: -0.0003

Data Index: 652022 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5021. Min Act: -0.0003

Data Index: 1162065 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.5009. Min Act: -0.0002

Data Index: 633621 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4988. Min Act: -0.0002

Data Index: 733289 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4878. Min Act: -0.0002

Data Index: 18245 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4908. Min Act: -0.0002

Data Index: 958465 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4753. Min Act: -0.0003

Data Index: 400597 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4685. Min Act: -0.0002

Data Index: 699176 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4193. Min Act: -0.0002

Data Index: 1024322 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.4159. Min Act: -0.0002

Data Index: 255326 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 0.6388. Min Range: -0.6388

Max Act: 0.3965. Min Act: -0.0002

Data Index: 374623 (C4 (Web Text))

Max Activating Token Index: 693