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

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

Neuron 1039 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: 1.3120. Min Range: -1.3120

Max Act: 1.2552. Min Act: -0.0000

Data Index: 384049 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.1859. Min Act: -0.0000

Data Index: 308856 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.3120. Min Act: -0.0000

Data Index: 229484 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.2296. Min Act: -0.0000

Data Index: 705845 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.2768. Min Act: -0.0000

Data Index: 822513 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0959. Min Act: -0.0000

Data Index: 899985 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0607. Min Act: -0.0000

Data Index: 179090 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1154592 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9870. Min Act: -0.0000

Data Index: 205210 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0338. Min Act: -0.0000

Data Index: 1250122 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 1.3120. Min Range: -1.3120

Max Act: 1.0572. Min Act: -0.0000

Data Index: 281228 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9226. Min Act: -0.0000

Data Index: 1303118 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1118227 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9198. Min Act: -0.0000

Data Index: 50765 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1138525 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9804. Min Act: -0.0000

Data Index: 203448 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.8637. Min Act: -0.0000

Data Index: 825532 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9392. Min Act: -0.0000

Data Index: 376894 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.8566. Min Act: -0.0000

Data Index: 595608 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 1.3120. Min Range: -1.3120

Max Act: 0.9228. Min Act: -0.0000

Data Index: 824666 (C4 (Web Text))

Max Activating Token Index: 472