Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1457 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.9287. Min Act: -0.0000

Data Index: 951143 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1190675 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7769. Min Act: -0.0000

Data Index: 701099 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1150209 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1310562 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1073043 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7342. Min Act: -0.0000

Data Index: 393055 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1244982 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7231. Min Act: -0.0000

Data Index: 606792 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1613279 (Python Code)

Max Activating Token Index: 482

Text #10

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6973. Min Act: -0.0000

Data Index: 906484 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6718. Min Act: -0.0000

Data Index: 660879 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6664. Min Act: -0.0000

Data Index: 96614 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1147824 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6785. Min Act: -0.0000

Data Index: 831845 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1127739 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6780. Min Act: -0.0000

Data Index: 377772 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6591. Min Act: -0.0000

Data Index: 929425 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1109598 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.9287. Min Range: -0.9287

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1559039 (Python Code)

Max Activating Token Index: 566