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

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

Neuron 4004 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: 0.9954. Min Range: -0.9954

Max Act: 0.9954. Min Act: -0.0002

Data Index: 1311100 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9693. Min Act: -0.0002

Data Index: 770073 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9695. Min Act: -0.0002

Data Index: 618165 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9384. Min Act: -0.0002

Data Index: 1170220 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9568. Min Act: -0.0002

Data Index: 464013 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9427. Min Act: -0.0002

Data Index: 605121 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9199. Min Act: -0.0002

Data Index: 298685 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9122. Min Act: -0.0002

Data Index: 442305 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.9001. Min Act: -0.0002

Data Index: 1235185 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8824. Min Act: -0.0002

Data Index: 1041972 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8959. Min Act: -0.0002

Data Index: 312396 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8856. Min Act: -0.0002

Data Index: 337889 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8752. Min Act: -0.0002

Data Index: 1313135 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8706. Min Act: -0.0002

Data Index: 391098 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8733. Min Act: -0.0002

Data Index: 1239246 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8731. Min Act: -0.0002

Data Index: 443601 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8554. Min Act: -0.0002

Data Index: 279743 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8810. Min Act: -0.0002

Data Index: 162060 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8822. Min Act: -0.0002

Data Index: 350977 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.9954. Min Range: -0.9954

Max Act: 0.8775. Min Act: -0.0002

Data Index: 672314 (C4 (Web Text))

Max Activating Token Index: 89