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

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

Neuron 737 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.4109. Min Act: -0.0000

Data Index: 314760 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.4152. Min Act: -0.0000

Data Index: 797221 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.3798. Min Act: -0.0000

Data Index: 334170 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.3721. Min Act: -0.0000

Data Index: 330493 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1069133 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2871. Min Act: -0.0000

Data Index: 52900 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.3029. Min Act: -0.0000

Data Index: 114389 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2880. Min Act: -0.0000

Data Index: 837068 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2833. Min Act: -0.0000

Data Index: 700807 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2804. Min Act: -0.0000

Data Index: 774329 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2794. Min Act: -0.0000

Data Index: 344086 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1131339 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2686. Min Act: -0.0000

Data Index: 82883 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2600. Min Act: -0.0000

Data Index: 310403 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1337205 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2630. Min Act: -0.0000

Data Index: 906820 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2554. Min Act: -0.0000

Data Index: 929679 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2611. Min Act: -0.0000

Data Index: 723748 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1044166 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.4152. Min Range: -0.4152

Max Act: 0.2572. Min Act: -0.0000

Data Index: 503571 (C4 (Web Text))

Max Activating Token Index: 153