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

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

Neuron 279 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1457344 (Python Code)

Max Activating Token Index: 544

Text #1

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2793. Min Act: -0.0000

Data Index: 442814 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1563980 (Python Code)

Max Activating Token Index: 104

Text #3

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2618. Min Act: -0.0000

Data Index: 540663 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1486063 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2809. Min Act: -0.0001

Data Index: 710449 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1192962 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2408. Min Act: -0.0001

Data Index: 1247217 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2281. Min Act: -0.0001

Data Index: 624843 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1126449 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2129. Min Act: -0.0001

Data Index: 483217 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1107360 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1096016 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1927. Min Act: -0.0000

Data Index: 234291 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1294922 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1595932 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1870. Min Act: -0.0000

Data Index: 257497 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1728. Min Act: -0.0000

Data Index: 570456 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1709. Min Act: -0.0000

Data Index: 473658 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.2949. Min Range: -0.2949

Max Act: 0.1718. Min Act: -0.0000

Data Index: 579186 (C4 (Web Text))

Max Activating Token Index: 653