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

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

Neuron 5512 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7745. Min Act: -0.0002

Data Index: 716796 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6899. Min Act: -0.0002

Data Index: 477937 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6984. Min Act: -0.0002

Data Index: 640927 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6703. Min Act: -0.0003

Data Index: 489504 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6661. Min Act: -0.0002

Data Index: 465952 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6634. Min Act: -0.0002

Data Index: 1213859 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6700. Min Act: -0.0002

Data Index: 1110926 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6570. Min Act: -0.0002

Data Index: 188194 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6570. Min Act: -0.0002

Data Index: 1036853 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6570. Min Act: -0.0002

Data Index: 311837 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6594. Min Act: -0.0003

Data Index: 1337581 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6652. Min Act: -0.0002

Data Index: 1232782 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6510. Min Act: -0.0002

Data Index: 751693 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6623. Min Act: -0.0002

Data Index: 506009 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6664. Min Act: -0.0002

Data Index: 417508 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6465. Min Act: -0.0002

Data Index: 83324 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6577. Min Act: -0.0002

Data Index: 838147 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6640. Min Act: -0.0002

Data Index: 1181742 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6566. Min Act: -0.0003

Data Index: 1137209 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6657. Min Act: -0.0003

Data Index: 546911 (C4 (Web Text))

Max Activating Token Index: 800