Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 975 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.6427. Min Act: -0.0001

Data Index: 1238919 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5740. Min Act: -0.0002

Data Index: 649762 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5048. Min Act: -0.0001

Data Index: 797704 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5490. Min Act: -0.0001

Data Index: 1057003 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5471. Min Act: -0.0002

Data Index: 500103 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5044. Min Act: -0.0002

Data Index: 1337401 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5125. Min Act: -0.0001

Data Index: 1317387 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5075. Min Act: -0.0001

Data Index: 1402052 (Python Code)

Max Activating Token Index: 839

Text #8

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4752. Min Act: -0.0001

Data Index: 980954 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4673. Min Act: -0.0001

Data Index: 1083452 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4685. Min Act: -0.0002

Data Index: 54172 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4682. Min Act: -0.0002

Data Index: 415335 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4960. Min Act: -0.0002

Data Index: 848234 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4653. Min Act: -0.0002

Data Index: 480 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4664. Min Act: -0.0001

Data Index: 1232803 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4687. Min Act: -0.0002

Data Index: 48267 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4818. Min Act: -0.0001

Data Index: 1635802 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4432. Min Act: -0.0002

Data Index: 369686 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4583. Min Act: -0.0002

Data Index: 1265328 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4423. Min Act: -0.0001

Data Index: 147513 (C4 (Web Text))

Max Activating Token Index: 34