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

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

Neuron 4038 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: 0.7109. Min Range: -0.7109

Max Act: 0.7109. Min Act: -0.0001

Data Index: 1502960 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6667. Min Act: -0.0001

Data Index: 1469141 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6676. Min Act: -0.0001

Data Index: 1403920 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6778. Min Act: -0.0001

Data Index: 1416130 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6526. Min Act: -0.0002

Data Index: 1433169 (Python Code)

Max Activating Token Index: 58

Text #5

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6436. Min Act: -0.0001

Data Index: 1627789 (Python Code)

Max Activating Token Index: 41

Text #6

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6505. Min Act: -0.0001

Data Index: 1482222 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1613747 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6609. Min Act: -0.0001

Data Index: 1512330 (Python Code)

Max Activating Token Index: 480

Text #9

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6364. Min Act: -0.0001

Data Index: 1617741 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6424. Min Act: -0.0001

Data Index: 943574 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5573. Min Act: -0.0001

Data Index: 1377444 (Python Code)

Max Activating Token Index: 674

Text #12

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1553787 (Python Code)

Max Activating Token Index: 218

Text #13

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5842. Min Act: -0.0001

Data Index: 1588704 (Python Code)

Max Activating Token Index: 1006

Text #14

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6159. Min Act: -0.0002

Data Index: 297204 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5736. Min Act: -0.0002

Data Index: 312604 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.6262. Min Act: -0.0001

Data Index: 307264 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5529. Min Act: -0.0001

Data Index: 1530009 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5884. Min Act: -0.0002

Data Index: 103042 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.7109. Min Range: -0.7109

Max Act: 0.5664. Min Act: -0.0002

Data Index: 300938 (C4 (Web Text))

Max Activating Token Index: 8