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

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

Neuron 431 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1039. Min Range: -3.1039

Max Act: 3.1039. Min Act: -0.0000

Data Index: 577492 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.8798. Min Act: -0.0000

Data Index: 191556 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.8634. Min Act: -0.0001

Data Index: 774185 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.3862. Min Act: -0.0000

Data Index: 1347149 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.4871. Min Act: -0.0000

Data Index: 634420 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.1610. Min Act: -0.0000

Data Index: 1305367 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.6625. Min Act: -0.0000

Data Index: 100517 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.5374. Min Act: -0.0000

Data Index: 1121244 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.1899. Min Act: -0.0000

Data Index: 1016828 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.0626. Min Act: -0.0000

Data Index: 133 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.2086. Min Act: -0.0000

Data Index: 1315266 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.1471. Min Act: -0.0000

Data Index: 1211439 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.1249. Min Act: -0.0000

Data Index: 120966 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.1242. Min Act: -0.0000

Data Index: 1158902 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.1780. Min Act: -0.0000

Data Index: 670406 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 3.1039. Min Range: -3.1039

Max Act: 1.9607. Min Act: -0.0000

Data Index: 596045 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 3.1039. Min Range: -3.1039

Max Act: 2.0551. Min Act: -0.0000

Data Index: 252480 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 3.1039. Min Range: -3.1039

Max Act: 1.9962. Min Act: -0.0000

Data Index: 810774 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 3.1039. Min Range: -3.1039

Max Act: 1.9839. Min Act: -0.0000

Data Index: 898997 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 3.1039. Min Range: -3.1039

Max Act: 1.7838. Min Act: -0.0000

Data Index: 1154291 (C4 (Web Text))

Max Activating Token Index: 718