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

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

Neuron 1629 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.9821. Min Act: -0.0001

Data Index: 529568 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.9400. Min Act: -0.0001

Data Index: 143336 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8409. Min Act: -0.0001

Data Index: 838617 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.6937. Min Act: -0.0001

Data Index: 1168951 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.9828. Min Act: -0.0001

Data Index: 445792 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8080. Min Act: -0.0001

Data Index: 344588 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7484. Min Act: -0.0001

Data Index: 473163 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7662. Min Act: -0.0001

Data Index: 1359500 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.6055. Min Act: -0.0001

Data Index: 1339540 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7432. Min Act: -0.0001

Data Index: 1256592 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7485. Min Act: -0.0001

Data Index: 1180179 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7669. Min Act: -0.0001

Data Index: 1314174 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8898. Min Act: -0.0001

Data Index: 711176 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7252. Min Act: -0.0001

Data Index: 1027255 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.5592. Min Act: -0.0001

Data Index: 834378 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7070. Min Act: -0.0001

Data Index: 1143699 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.8463. Min Act: -0.0001

Data Index: 390049 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.7050. Min Act: -0.0001

Data Index: 601947 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.3460. Min Act: -0.0001

Data Index: 57859 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 3.9828. Min Range: -3.9828

Max Act: 3.6585. Min Act: -0.0001

Data Index: 1141789 (C4 (Web Text))

Max Activating Token Index: 669