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

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

Neuron 2327 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: 3.3117. Min Range: -3.3117

Max Act: 2.7568. Min Act: -0.0000

Data Index: 1196617 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 3.3117. Min Range: -3.3117

Max Act: 3.3117. Min Act: -0.0000

Data Index: 1087052 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 3.3117. Min Range: -3.3117

Max Act: 3.2746. Min Act: -0.0000

Data Index: 1099137 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.9791. Min Act: -0.0000

Data Index: 762795 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.8077. Min Act: -0.0000

Data Index: 205295 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 3.3117. Min Range: -3.3117

Max Act: 3.0262. Min Act: -0.0000

Data Index: 713765 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.7472. Min Act: -0.0000

Data Index: 487813 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 3.3117. Min Range: -3.3117

Max Act: 3.0246. Min Act: -0.0001

Data Index: 176435 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.6651. Min Act: -0.0000

Data Index: 748557 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.6929. Min Act: -0.0000

Data Index: 459970 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.6473. Min Act: -0.0000

Data Index: 810428 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.6124. Min Act: -0.0000

Data Index: 879918 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.5980. Min Act: -0.0000

Data Index: 1277835 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.6783. Min Act: -0.0000

Data Index: 1258708 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.4011. Min Act: -0.0000

Data Index: 766724 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.6208. Min Act: -0.0000

Data Index: 1314883 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.3658. Min Act: -0.0000

Data Index: 642401 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.4973. Min Act: -0.0000

Data Index: 735805 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.5943. Min Act: -0.0000

Data Index: 1247554 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.3117. Min Range: -3.3117

Max Act: 2.5954. Min Act: -0.0000

Data Index: 17008 (C4 (Web Text))

Max Activating Token Index: 133