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

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

Neuron 4005 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7430. Min Range: -7.7430

Max Act: 7.7430. Min Act: -0.0000

Data Index: 85651 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 7.7430. Min Range: -7.7430

Max Act: 7.6191. Min Act: -0.0000

Data Index: 355799 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 7.7430. Min Range: -7.7430

Max Act: 7.2825. Min Act: -0.0001

Data Index: 1238395 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 7.7430. Min Range: -7.7430

Max Act: 7.4413. Min Act: -0.0000

Data Index: 24806 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 7.7430. Min Range: -7.7430

Max Act: 7.3040. Min Act: -0.0001

Data Index: 246931 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 7.7430. Min Range: -7.7430

Max Act: 7.2456. Min Act: -0.0001

Data Index: 597906 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 7.7430. Min Range: -7.7430

Max Act: 7.0660. Min Act: -0.0000

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.7386. Min Act: -0.0001

Data Index: 735295 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 7.7430. Min Range: -7.7430

Max Act: 7.3116. Min Act: -0.0001

Data Index: 847169 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.4331. Min Act: -0.0000

Data Index: 23919 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.9641. Min Act: -0.0000

Data Index: 172709 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.7071. Min Act: -0.0001

Data Index: 733206 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.6978. Min Act: -0.0000

Data Index: 151094 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.2136. Min Act: -0.0000

Data Index: 13946 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.2082. Min Act: -0.0000

Data Index: 675188 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.4597. Min Act: -0.0000

Data Index: 865299 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 7.7430. Min Range: -7.7430

Max Act: 5.8469. Min Act: -0.0001

Data Index: 285277 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.0418. Min Act: -0.0001

Data Index: 483801 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 7.7430. Min Range: -7.7430

Max Act: 6.2180. Min Act: -0.0000

Data Index: 41423 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 7.7430. Min Range: -7.7430

Max Act: 4.9121. Min Act: -0.0001

Data Index: 681635 (C4 (Web Text))

Max Activating Token Index: 746