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

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

Neuron 3905 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3869. Min Range: -1.3869

Max Act: 1.3869. Min Act: -0.0000

Data Index: 1165224 (C4 (Web Text))

Max Activating Token Index: 448

Text #1

Max Range: 1.3869. Min Range: -1.3869

Max Act: 1.1614. Min Act: -0.0000

Data Index: 428877 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 1.3869. Min Range: -1.3869

Max Act: 1.2030. Min Act: -0.0000

Data Index: 919740 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 1.3869. Min Range: -1.3869

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1103088 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.9353. Min Act: -0.0000

Data Index: 685491 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 1.3869. Min Range: -1.3869

Max Act: 1.0116. Min Act: -0.0000

Data Index: 886794 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.9832. Min Act: -0.0000

Data Index: 352879 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1061502 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1286025 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.3869. Min Range: -1.3869

Max Act: 1.0159. Min Act: -0.0000

Data Index: 840691 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.9472. Min Act: -0.0000

Data Index: 574766 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.8792. Min Act: -0.0000

Data Index: 894769 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1322579 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.7786. Min Act: -0.0000

Data Index: 113727 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1299387 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.8705. Min Act: -0.0000

Data Index: 580498 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.8766. Min Act: -0.0000

Data Index: 653545 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.7137. Min Act: -0.0000

Data Index: 5545 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.7735. Min Act: -0.0000

Data Index: 264523 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.3869. Min Range: -1.3869

Max Act: 0.7056. Min Act: -0.0000

Data Index: 72304 (C4 (Web Text))

Max Activating Token Index: 1011