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

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

Neuron 2739 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: 3.7023. Min Range: -3.7023

Max Act: 3.7023. Min Act: -0.0000

Data Index: 861444 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.6032. Min Act: -0.0000

Data Index: 159225 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.3938. Min Act: -0.0000

Data Index: 399364 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.5478. Min Act: -0.0000

Data Index: 1025687 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.3264. Min Act: -0.0000

Data Index: 384494 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.3559. Min Act: -0.0000

Data Index: 824561 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.2431. Min Act: -0.0000

Data Index: 856959 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.3826. Min Act: -0.0000

Data Index: 823940 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.3261. Min Act: -0.0000

Data Index: 1179655 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.8398. Min Act: -0.0000

Data Index: 54729 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 3.7023. Min Range: -3.7023

Max Act: 3.1204. Min Act: -0.0000

Data Index: 1030440 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.8318. Min Act: -0.0000

Data Index: 538325 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.8914. Min Act: -0.0000

Data Index: 742260 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.7606. Min Act: -0.0000

Data Index: 395846 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.8185. Min Act: -0.0000

Data Index: 90185 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.9159. Min Act: -0.0000

Data Index: 618479 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.7791. Min Act: -0.0000

Data Index: 799090 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.6575. Min Act: -0.0000

Data Index: 1282401 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.6407. Min Act: -0.0000

Data Index: 634175 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 3.7023. Min Range: -3.7023

Max Act: 2.6113. Min Act: -0.0000

Data Index: 671227 (C4 (Web Text))

Max Activating Token Index: 981