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

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

Neuron 6002 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: 2.5237. Min Range: -2.5237

Max Act: 2.5237. Min Act: -0.0002

Data Index: 594658 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 2.5237. Min Range: -2.5237

Max Act: 2.2083. Min Act: -0.0002

Data Index: 614623 (C4 (Web Text))

Max Activating Token Index: 396

Text #2

Max Range: 2.5237. Min Range: -2.5237

Max Act: 2.1667. Min Act: -0.0002

Data Index: 509593 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.9284. Min Act: -0.0002

Data Index: 1345851 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.8858. Min Act: -0.0002

Data Index: 649161 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.8839. Min Act: -0.0002

Data Index: 646777 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.8895. Min Act: -0.0003

Data Index: 695662 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.8531. Min Act: -0.0002

Data Index: 442975 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.8686. Min Act: -0.0002

Data Index: 235611 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.8377. Min Act: -0.0002

Data Index: 333575 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.8060. Min Act: -0.0002

Data Index: 1139408 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.7453. Min Act: -0.0002

Data Index: 903152 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.6609. Min Act: -0.0002

Data Index: 463033 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.6434. Min Act: -0.0002

Data Index: 131374 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.6522. Min Act: -0.0002

Data Index: 120417 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.6333. Min Act: -0.0002

Data Index: 332470 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.6042. Min Act: -0.0002

Data Index: 936682 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.5570. Min Act: -0.0002

Data Index: 1269522 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.6333. Min Act: -0.0002

Data Index: 179108 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 2.5237. Min Range: -2.5237

Max Act: 1.5076. Min Act: -0.0002

Data Index: 865314 (C4 (Web Text))

Max Activating Token Index: 283