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

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

Neuron 354 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.3675. Min Act: -0.0000

Data Index: 1582455 (Python Code)

Max Activating Token Index: 661

Text #1

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.2675. Min Act: -0.0000

Data Index: 1647504 (Python Code)

Max Activating Token Index: 372

Text #2

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.2308. Min Act: -0.0000

Data Index: 1409550 (Python Code)

Max Activating Token Index: 889

Text #3

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1568456 (Python Code)

Max Activating Token Index: 779

Text #4

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1531912 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.0113. Min Act: -0.0000

Data Index: 1441170 (Python Code)

Max Activating Token Index: 651

Text #6

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.0092. Min Act: -0.0000

Data Index: 1388681 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 1.3675. Min Range: -1.3675

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1584561 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1585928 (Python Code)

Max Activating Token Index: 714

Text #9

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1573557 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1608165 (Python Code)

Max Activating Token Index: 438

Text #11

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1595159 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1438096 (Python Code)

Max Activating Token Index: 668

Text #13

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1438012 (Python Code)

Max Activating Token Index: 939

Text #14

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1533957 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1487053 (Python Code)

Max Activating Token Index: 767

Text #16

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1478214 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1571586 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1459659 (Python Code)

Max Activating Token Index: 888

Text #19

Max Range: 1.3675. Min Range: -1.3675

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1517853 (Python Code)

Max Activating Token Index: 228