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

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

Neuron 4440 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3885. Min Act: 0.0000

Data Index: 1339039 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3763. Min Act: -0.0000

Data Index: 38874 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1368946 (Python Code)

Max Activating Token Index: 823

Text #3

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3533. Min Act: -0.0000

Data Index: 578362 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1526116 (Python Code)

Max Activating Token Index: 929

Text #5

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3624. Min Act: -0.0000

Data Index: 399905 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3385. Min Act: -0.0000

Data Index: 829916 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3449. Min Act: -0.0000

Data Index: 287815 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1277951 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3303. Min Act: -0.0000

Data Index: 24621 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1098355 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3087. Min Act: -0.0000

Data Index: 501691 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3129. Min Act: -0.0000

Data Index: 703767 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1261010 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3097. Min Act: -0.0000

Data Index: 384564 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3049. Min Act: -0.0000

Data Index: 740471 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3061. Min Act: 0.0001

Data Index: 57593 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3038. Min Act: -0.0000

Data Index: 1029340 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1624486 (Python Code)

Max Activating Token Index: 877

Text #19

Max Range: 0.3885. Min Range: -0.3885

Max Act: 0.3006. Min Act: -0.0000

Data Index: 1547688 (Python Code)

Max Activating Token Index: 801