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

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

Neuron 2600 in Layer 0

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: 0.9401. Min Range: -0.9401

Max Act: 0.9401. Min Act: -0.0001

Data Index: 156180 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.9224. Min Act: -0.0001

Data Index: 1264100 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.9052. Min Act: -0.0001

Data Index: 550261 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.9111. Min Act: -0.0001

Data Index: 571668 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.9030. Min Act: -0.0001

Data Index: 1002101 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.9092. Min Act: -0.0001

Data Index: 243857 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8965. Min Act: -0.0001

Data Index: 359785 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8813. Min Act: -0.0001

Data Index: 83380 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8588. Min Act: -0.0001

Data Index: 731948 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8680. Min Act: -0.0002

Data Index: 430866 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8719. Min Act: -0.0001

Data Index: 365605 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8601. Min Act: -0.0001

Data Index: 638594 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8401. Min Act: -0.0001

Data Index: 612255 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8284. Min Act: -0.0002

Data Index: 325279 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8226. Min Act: -0.0001

Data Index: 64271 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8428. Min Act: -0.0001

Data Index: 993344 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8294. Min Act: -0.0001

Data Index: 942262 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8284. Min Act: -0.0001

Data Index: 921515 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8351. Min Act: -0.0001

Data Index: 1187106 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.9401. Min Range: -0.9401

Max Act: 0.8298. Min Act: -0.0001

Data Index: 954012 (C4 (Web Text))

Max Activating Token Index: 1023