Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2147 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0463. Min Range: -2.0463

Max Act: 2.0463. Min Act: -0.0000

Data Index: 981659 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7641. Min Act: -0.0000

Data Index: 27843 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.9090. Min Act: -0.0000

Data Index: 496576 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.8525. Min Act: -0.0000

Data Index: 390824 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.8708. Min Act: -0.0000

Data Index: 424978 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7485. Min Act: -0.0000

Data Index: 661645 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7745. Min Act: -0.0000

Data Index: 821421 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.8080. Min Act: -0.0000

Data Index: 1151978 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7899. Min Act: -0.0000

Data Index: 1144772 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7745. Min Act: -0.0000

Data Index: 132871 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.6998. Min Act: -0.0000

Data Index: 622415 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7462. Min Act: -0.0000

Data Index: 71968 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.5971. Min Act: -0.0000

Data Index: 580754 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7215. Min Act: -0.0000

Data Index: 816868 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.6334. Min Act: -0.0000

Data Index: 1060543 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.6277. Min Act: -0.0000

Data Index: 700470 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.7167. Min Act: -0.0000

Data Index: 146629 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.6779. Min Act: -0.0000

Data Index: 1027450 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.6206. Min Act: -0.0000

Data Index: 384181 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 2.0463. Min Range: -2.0463

Max Act: 1.6618. Min Act: -0.0000

Data Index: 1350127 (C4 (Web Text))

Max Activating Token Index: 521