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

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

Neuron 4402 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.7035. Min Act: -0.0000

Data Index: 968854 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.7855. Min Act: -0.0000

Data Index: 371257 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.6649. Min Act: -0.0000

Data Index: 520824 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.7440. Min Act: -0.0000

Data Index: 705592 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.5139. Min Act: -0.0000

Data Index: 375352 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.6344. Min Act: -0.0000

Data Index: 177479 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1303782 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.5161. Min Act: -0.0000

Data Index: 626407 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.4819. Min Act: -0.0000

Data Index: 73299 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.4544. Min Act: -0.0000

Data Index: 701450 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.4076. Min Act: -0.0000

Data Index: 140126 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.4012. Min Act: -0.0000

Data Index: 1178156 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.4876. Min Act: -0.0000

Data Index: 1349337 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.3858. Min Act: -0.0000

Data Index: 424513 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.3787. Min Act: -0.0000

Data Index: 166936 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.3651. Min Act: -0.0000

Data Index: 840823 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.3827. Min Act: -0.0000

Data Index: 777917 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.3293. Min Act: -0.0000

Data Index: 79150 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.4032. Min Act: -0.0000

Data Index: 954903 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.7855. Min Range: -1.7855

Max Act: 1.3137. Min Act: -0.0000

Data Index: 842156 (C4 (Web Text))

Max Activating Token Index: 85