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

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

Neuron 623 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: 3.4366. Min Range: -3.4366

Max Act: 3.4366. Min Act: -0.0000

Data Index: 888681 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 3.4366. Min Range: -3.4366

Max Act: 3.1103. Min Act: -0.0000

Data Index: 532770 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.4366. Min Range: -3.4366

Max Act: 3.0987. Min Act: -0.0000

Data Index: 37836 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 3.4366. Min Range: -3.4366

Max Act: 3.0483. Min Act: -0.0000

Data Index: 256256 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.9456. Min Act: -0.0000

Data Index: 231378 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.9216. Min Act: -0.0000

Data Index: 1245513 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.8918. Min Act: -0.0000

Data Index: 86923 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.7241. Min Act: -0.0000

Data Index: 1346794 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.8284. Min Act: -0.0000

Data Index: 42200 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.8015. Min Act: -0.0000

Data Index: 745973 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.6613. Min Act: -0.0000

Data Index: 1013132 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.7396. Min Act: -0.0000

Data Index: 705910 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.7281. Min Act: -0.0000

Data Index: 1099697 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.7330. Min Act: -0.0000

Data Index: 486982 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.7403. Min Act: -0.0000

Data Index: 523878 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.6734. Min Act: -0.0000

Data Index: 1225109 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.5225. Min Act: -0.0000

Data Index: 1209815 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.6290. Min Act: -0.0000

Data Index: 1217083 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.7467. Min Act: -0.0000

Data Index: 722403 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 3.4366. Min Range: -3.4366

Max Act: 2.7169. Min Act: -0.0000

Data Index: 772016 (C4 (Web Text))

Max Activating Token Index: 285