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

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

Neuron 3629 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: 5.5656. Min Range: -5.5656

Max Act: 5.3069. Min Act: -0.0000

Data Index: 172937 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 5.5656. Min Range: -5.5656

Max Act: 5.2226. Min Act: -0.0000

Data Index: 59669 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 5.5656. Min Range: -5.5656

Max Act: 5.0530. Min Act: -0.0000

Data Index: 495992 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 5.5656. Min Range: -5.5656

Max Act: 5.0285. Min Act: -0.0000

Data Index: 94508 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 5.5656. Min Range: -5.5656

Max Act: 4.7991. Min Act: -0.0000

Data Index: 407002 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 5.5656. Min Range: -5.5656

Max Act: 5.5656. Min Act: -0.0000

Data Index: 1199525 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 5.5656. Min Range: -5.5656

Max Act: 5.4495. Min Act: -0.0000

Data Index: 1241260 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 5.5656. Min Range: -5.5656

Max Act: 4.7367. Min Act: -0.0000

Data Index: 504663 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 5.5656. Min Range: -5.5656

Max Act: 4.5751. Min Act: -0.0000

Data Index: 26171 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 5.5656. Min Range: -5.5656

Max Act: 3.6919. Min Act: -0.0000

Data Index: 1043406 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 5.5656. Min Range: -5.5656

Max Act: 3.6872. Min Act: -0.0000

Data Index: 1037260 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 5.5656. Min Range: -5.5656

Max Act: 3.3642. Min Act: -0.0000

Data Index: 127143 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 5.5656. Min Range: -5.5656

Max Act: 3.4276. Min Act: -0.0000

Data Index: 843321 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 5.5656. Min Range: -5.5656

Max Act: 3.3158. Min Act: -0.0000

Data Index: 594954 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 5.5656. Min Range: -5.5656

Max Act: 3.2811. Min Act: -0.0000

Data Index: 988077 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 5.5656. Min Range: -5.5656

Max Act: 3.1156. Min Act: -0.0000

Data Index: 7063 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 5.5656. Min Range: -5.5656

Max Act: 3.0403. Min Act: -0.0000

Data Index: 191580 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 5.5656. Min Range: -5.5656

Max Act: 2.9627. Min Act: -0.0000

Data Index: 55131 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 5.5656. Min Range: -5.5656

Max Act: 2.9358. Min Act: -0.0000

Data Index: 213402 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 5.5656. Min Range: -5.5656

Max Act: 2.9366. Min Act: -0.0000

Data Index: 799033 (C4 (Web Text))

Max Activating Token Index: 314