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

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

Neuron 5068 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: 0.9895. Min Range: -0.9895

Max Act: 0.9895. Min Act: -0.0003

Data Index: 1162169 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9714. Min Act: -0.0002

Data Index: 30232 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9715. Min Act: -0.0002

Data Index: 1180049 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9567. Min Act: -0.0002

Data Index: 1035542 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9602. Min Act: -0.0002

Data Index: 428504 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9634. Min Act: -0.0002

Data Index: 823137 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9524. Min Act: -0.0002

Data Index: 67059 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9267. Min Act: -0.0002

Data Index: 625789 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9338. Min Act: -0.0002

Data Index: 404548 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9128. Min Act: -0.0002

Data Index: 1217582 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9281. Min Act: -0.0002

Data Index: 808231 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9150. Min Act: -0.0002

Data Index: 212177 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9258. Min Act: -0.0002

Data Index: 144961 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9013. Min Act: -0.0002

Data Index: 142452 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9126. Min Act: -0.0002

Data Index: 682404 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9033. Min Act: -0.0003

Data Index: 823146 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.9063. Min Act: -0.0002

Data Index: 347776 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.8926. Min Act: -0.0003

Data Index: 972900 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.8968. Min Act: -0.0002

Data Index: 507177 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.9895. Min Range: -0.9895

Max Act: 0.8894. Min Act: -0.0003

Data Index: 434448 (C4 (Web Text))

Max Activating Token Index: 146