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

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

Neuron 5418 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.9210. Min Act: -0.0000

Data Index: 1223802 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.8827. Min Act: -0.0000

Data Index: 803472 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.6009. Min Act: -0.0000

Data Index: 732980 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.6819. Min Act: -0.0000

Data Index: 885818 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.7654. Min Act: -0.0000

Data Index: 1132015 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.5397. Min Act: -0.0000

Data Index: 495699 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.5104. Min Act: -0.0000

Data Index: 368931 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.3488. Min Act: -0.0000

Data Index: 485276 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.4718. Min Act: -0.0000

Data Index: 189957 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.4605. Min Act: -0.0000

Data Index: 1129350 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.5235. Min Act: -0.0000

Data Index: 888106 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.3785. Min Act: -0.0000

Data Index: 1008502 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2287. Min Act: -0.0000

Data Index: 455148 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.3348. Min Act: -0.0000

Data Index: 885305 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.4194. Min Act: -0.0000

Data Index: 24203 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2956. Min Act: -0.0000

Data Index: 983243 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2776. Min Act: -0.0000

Data Index: 509478 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2815. Min Act: -0.0000

Data Index: 521739 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.1409. Min Act: -0.0000

Data Index: 893660 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 2.9210. Min Range: -2.9210

Max Act: 2.2267. Min Act: -0.0000

Data Index: 119085 (C4 (Web Text))

Max Activating Token Index: 578