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

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

Neuron 2076 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1630695 (Python Code)

Max Activating Token Index: 536

Text #1

Max Range: 1.0073. Min Range: -1.0073

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1604656 (Python Code)

Max Activating Token Index: 648

Text #2

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1591109 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.8091. Min Act: -0.0000

Data Index: 896742 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1271634 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1267986 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1375143 (Python Code)

Max Activating Token Index: 699

Text #7

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.7178. Min Act: -0.0000

Data Index: 580206 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1082084 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.7149. Min Act: -0.0000

Data Index: 1339611 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1542708 (Python Code)

Max Activating Token Index: 390

Text #11

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1652645 (Python Code)

Max Activating Token Index: 826

Text #12

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.6526. Min Act: -0.0000

Data Index: 597254 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1633703 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.7157. Min Act: -0.0000

Data Index: 200836 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.7063. Min Act: -0.0000

Data Index: 878905 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.6583. Min Act: 0.0000

Data Index: 1012817 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1519880 (Python Code)

Max Activating Token Index: 663

Text #18

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.6249. Min Act: 0.0000

Data Index: 152932 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 1.0073. Min Range: -1.0073

Max Act: 0.6387. Min Act: -0.0000

Data Index: 10755 (C4 (Web Text))

Max Activating Token Index: 517