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

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

Neuron 1215 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: 0.9471. Min Range: -0.9471

Max Act: 0.9471. Min Act: -0.0002

Data Index: 1118912 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8773. Min Act: -0.0002

Data Index: 1300817 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.8350. Min Act: -0.0002

Data Index: 669868 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7400. Min Act: -0.0002

Data Index: 1134535 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7361. Min Act: -0.0002

Data Index: 800843 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7124. Min Act: -0.0002

Data Index: 629051 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7141. Min Act: -0.0002

Data Index: 1097721 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7230. Min Act: -0.0002

Data Index: 758801 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7290. Min Act: -0.0002

Data Index: 1073731 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7191. Min Act: -0.0002

Data Index: 1352779 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.7117. Min Act: -0.0002

Data Index: 399957 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.6952. Min Act: -0.0002

Data Index: 424907 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.6775. Min Act: -0.0002

Data Index: 1395556 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.6696. Min Act: -0.0002

Data Index: 895006 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.6413. Min Act: -0.0002

Data Index: 704264 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.6534. Min Act: -0.0002

Data Index: 487133 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.6718. Min Act: -0.0002

Data Index: 970399 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.6326. Min Act: -0.0002

Data Index: 982631 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.6219. Min Act: -0.0002

Data Index: 767759 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.9471. Min Range: -0.9471

Max Act: 0.6410. Min Act: -0.0002

Data Index: 251693 (C4 (Web Text))

Max Activating Token Index: 87