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

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

Neuron 2160 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: 1.9519. Min Range: -1.9519

Max Act: 1.9519. Min Act: -0.0002

Data Index: 274002 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.8183. Min Act: -0.0002

Data Index: 1034630 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.7282. Min Act: -0.0002

Data Index: 685931 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.6219. Min Act: -0.0002

Data Index: 530593 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.6176. Min Act: -0.0002

Data Index: 783800 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.4974. Min Act: -0.0002

Data Index: 882164 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.5143. Min Act: -0.0002

Data Index: 566181 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.5303. Min Act: -0.0002

Data Index: 1291363 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.4841. Min Act: -0.0002

Data Index: 1198265 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.4754. Min Act: -0.0002

Data Index: 1343083 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.4806. Min Act: -0.0002

Data Index: 38833 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.4013. Min Act: -0.0002

Data Index: 53951 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.4093. Min Act: -0.0002

Data Index: 340467 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.4300. Min Act: -0.0002

Data Index: 326097 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.3814. Min Act: -0.0002

Data Index: 346270 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.4044. Min Act: -0.0002

Data Index: 1021314 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.3420. Min Act: -0.0002

Data Index: 1339619 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.3436. Min Act: -0.0002

Data Index: 759599 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.3538. Min Act: -0.0002

Data Index: 1065932 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 1.9519. Min Range: -1.9519

Max Act: 1.2795. Min Act: -0.0002

Data Index: 263924 (C4 (Web Text))

Max Activating Token Index: 823