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

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

Neuron 1222 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: 1.0562. Min Range: -1.0562

Max Act: 1.0536. Min Act: -0.0002

Data Index: 830855 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.0562. Min Range: -1.0562

Max Act: 1.0562. Min Act: -0.0002

Data Index: 974363 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 1.0562. Min Range: -1.0562

Max Act: 1.0223. Min Act: -0.0002

Data Index: 804748 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 1.0562. Min Range: -1.0562

Max Act: 1.0027. Min Act: -0.0002

Data Index: 1487 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 1.0562. Min Range: -1.0562

Max Act: 1.0092. Min Act: -0.0002

Data Index: 778083 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9992. Min Act: -0.0002

Data Index: 26499 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9850. Min Act: -0.0002

Data Index: 353605 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9592. Min Act: -0.0002

Data Index: 1072431 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9762. Min Act: -0.0002

Data Index: 129612 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9632. Min Act: -0.0002

Data Index: 1214517 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9575. Min Act: -0.0002

Data Index: 161116 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9507. Min Act: -0.0002

Data Index: 367628 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9264. Min Act: -0.0002

Data Index: 75269 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9242. Min Act: -0.0002

Data Index: 759004 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9298. Min Act: -0.0002

Data Index: 1105606 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9464. Min Act: -0.0002

Data Index: 1189793 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9406. Min Act: -0.0002

Data Index: 640501 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9542. Min Act: -0.0002

Data Index: 737467 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9131. Min Act: -0.0002

Data Index: 1287612 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 1.0562. Min Range: -1.0562

Max Act: 0.9178. Min Act: -0.0002

Data Index: 1274999 (C4 (Web Text))

Max Activating Token Index: 48