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

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

Neuron 4893 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0535. Min Range: -2.0535

Max Act: 2.0535. Min Act: -0.0000

Data Index: 258375 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 2.0535. Min Range: -2.0535

Max Act: 2.0161. Min Act: -0.0000

Data Index: 652891 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.7066. Min Act: -0.0000

Data Index: 388434 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.7025. Min Act: -0.0000

Data Index: 401294 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.8795. Min Act: -0.0000

Data Index: 777817 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.6807. Min Act: -0.0000

Data Index: 773751 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.6622. Min Act: -0.0000

Data Index: 216569 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.7147. Min Act: -0.0000

Data Index: 1105389 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.5965. Min Act: -0.0000

Data Index: 54627 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.6815. Min Act: -0.0000

Data Index: 1188059 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.6303. Min Act: -0.0000

Data Index: 1052234 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.6851. Min Act: -0.0000

Data Index: 46005 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.5759. Min Act: -0.0000

Data Index: 523701 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.5208. Min Act: -0.0000

Data Index: 304194 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.4918. Min Act: -0.0000

Data Index: 438013 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.4988. Min Act: -0.0000

Data Index: 573499 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.4877. Min Act: -0.0000

Data Index: 634277 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.5166. Min Act: -0.0000

Data Index: 712551 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.5234. Min Act: -0.0000

Data Index: 1036371 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 2.0535. Min Range: -2.0535

Max Act: 1.5563. Min Act: -0.0000

Data Index: 839065 (C4 (Web Text))

Max Activating Token Index: 148