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

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

Neuron 4784 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1361735 (Python Code)

Max Activating Token Index: 724

Text #1

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1333866 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1358329 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6123. Min Act: -0.0000

Data Index: 945065 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1028538 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6409. Min Act: -0.0000

Data Index: 783685 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1109270 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5827. Min Act: -0.0000

Data Index: 1080409 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6012. Min Act: -0.0000

Data Index: 401794 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6022. Min Act: -0.0000

Data Index: 725234 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1022937 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5940. Min Act: -0.0000

Data Index: 600032 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1022480 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6122. Min Act: -0.0000

Data Index: 577575 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5745. Min Act: -0.0000

Data Index: 849662 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5703. Min Act: -0.0000

Data Index: 938276 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1298455 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6027. Min Act: -0.0000

Data Index: 872718 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5927. Min Act: -0.0000

Data Index: 619933 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1218593 (C4 (Web Text))

Max Activating Token Index: 850