Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1294 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.6391. Min Range: -4.6391

Max Act: 4.6391. Min Act: -0.0000

Data Index: 1518323 (Python Code)

Max Activating Token Index: 84

Text #1

Max Range: 4.6391. Min Range: -4.6391

Max Act: 4.2378. Min Act: -0.0000

Data Index: 1526989 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 4.6391. Min Range: -4.6391

Max Act: 4.2195. Min Act: -0.0000

Data Index: 1638312 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.9818. Min Act: -0.0000

Data Index: 1450157 (Python Code)

Max Activating Token Index: 365

Text #4

Max Range: 4.6391. Min Range: -4.6391

Max Act: 4.1621. Min Act: -0.0000

Data Index: 1649009 (Python Code)

Max Activating Token Index: 478

Text #5

Max Range: 4.6391. Min Range: -4.6391

Max Act: 4.0489. Min Act: -0.0000

Data Index: 1460700 (Python Code)

Max Activating Token Index: 78

Text #6

Max Range: 4.6391. Min Range: -4.6391

Max Act: 4.1637. Min Act: -0.0000

Data Index: 1016639 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.9959. Min Act: -0.0000

Data Index: 1376209 (Python Code)

Max Activating Token Index: 956

Text #8

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.9714. Min Act: -0.0000

Data Index: 1377250 (Python Code)

Max Activating Token Index: 336

Text #9

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.7749. Min Act: -0.0000

Data Index: 1488214 (Python Code)

Max Activating Token Index: 532

Text #10

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.7527. Min Act: -0.0000

Data Index: 1522591 (Python Code)

Max Activating Token Index: 478

Text #11

Max Range: 4.6391. Min Range: -4.6391

Max Act: 4.0126. Min Act: -0.0000

Data Index: 1525658 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.7970. Min Act: -0.0000

Data Index: 1363501 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.5875. Min Act: -0.0000

Data Index: 1464796 (Python Code)

Max Activating Token Index: 719

Text #14

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.8417. Min Act: -0.0000

Data Index: 1632130 (Python Code)

Max Activating Token Index: 146

Text #15

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.7310. Min Act: -0.0000

Data Index: 1646969 (Python Code)

Max Activating Token Index: 990

Text #16

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.5067. Min Act: -0.0000

Data Index: 1375446 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.5914. Min Act: -0.0000

Data Index: 1578050 (Python Code)

Max Activating Token Index: 492

Text #18

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.5598. Min Act: -0.0000

Data Index: 1478906 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 4.6391. Min Range: -4.6391

Max Act: 3.5532. Min Act: -0.0000

Data Index: 1242396 (C4 (Web Text))

Max Activating Token Index: 566