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

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

Neuron 3204 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: 1.4527. Min Range: -1.4527

Max Act: 1.4527. Min Act: -0.0000

Data Index: 945991 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 1.4527. Min Range: -1.4527

Max Act: 1.1412. Min Act: -0.0000

Data Index: 5846 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.4527. Min Range: -1.4527

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1315772 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.4527. Min Range: -1.4527

Max Act: 1.0591. Min Act: -0.0000

Data Index: 95329 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9715. Min Act: -0.0000

Data Index: 56596 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 1.4527. Min Range: -1.4527

Max Act: 1.0291. Min Act: -0.0000

Data Index: 1179724 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9673. Min Act: -0.0000

Data Index: 696696 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9694. Min Act: -0.0000

Data Index: 269464 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1223221 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1179969 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9290. Min Act: -0.0000

Data Index: 749292 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9056. Min Act: -0.0000

Data Index: 670176 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9234. Min Act: -0.0000

Data Index: 482866 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9207. Min Act: -0.0000

Data Index: 147543 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.8532. Min Act: -0.0000

Data Index: 363131 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9085. Min Act: -0.0000

Data Index: 728586 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9135. Min Act: -0.0000

Data Index: 811589 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9112. Min Act: -0.0000

Data Index: 499211 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1219626 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 1.4527. Min Range: -1.4527

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1263362 (C4 (Web Text))

Max Activating Token Index: 919