Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2423 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6112. Min Act: -0.0001

Data Index: 263592 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.6007. Min Act: -0.0001

Data Index: 1302643 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.7649. Min Act: -0.0001

Data Index: 123573 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5400. Min Act: -0.0001

Data Index: 281097 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5415. Min Act: -0.0001

Data Index: 569627 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1015367 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5574. Min Act: -0.0001

Data Index: 1322353 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5329. Min Act: -0.0001

Data Index: 617845 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5345. Min Act: -0.0001

Data Index: 459084 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5265. Min Act: -0.0001

Data Index: 542478 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5309. Min Act: -0.0001

Data Index: 107256 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5002. Min Act: -0.0001

Data Index: 1178025 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5149. Min Act: -0.0001

Data Index: 2472 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5073. Min Act: -0.0001

Data Index: 81759 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.4958. Min Act: -0.0001

Data Index: 672607 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5068. Min Act: -0.0001

Data Index: 948867 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.5190. Min Act: -0.0001

Data Index: 232219 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.4910. Min Act: -0.0001

Data Index: 557730 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.4672. Min Act: -0.0001

Data Index: 1284037 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.7649. Min Range: -0.7649

Max Act: 0.4683. Min Act: -0.0001

Data Index: 788863 (C4 (Web Text))

Max Activating Token Index: 651