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

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

Neuron 4368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2807. Min Act: -0.0001

Data Index: 846626 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2679. Min Act: -0.0001

Data Index: 1216403 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2839. Min Act: -0.0001

Data Index: 263612 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2280. Min Act: -0.0001

Data Index: 427151 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1532. Min Act: -0.0001

Data Index: 1193937 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1130. Min Act: -0.0001

Data Index: 1175814 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0357. Min Act: -0.0001

Data Index: 373851 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1326. Min Act: -0.0001

Data Index: 192625 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0688. Min Act: -0.0001

Data Index: 788241 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9694. Min Act: -0.0001

Data Index: 599984 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9808. Min Act: -0.0001

Data Index: 440085 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9129. Min Act: -0.0001

Data Index: 979423 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9532. Min Act: -0.0001

Data Index: 382641 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9494. Min Act: -0.0001

Data Index: 1300858 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9192. Min Act: -0.0001

Data Index: 1283736 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.8688. Min Act: -0.0001

Data Index: 1122359 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.8886. Min Act: -0.0001

Data Index: 314581 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.8824. Min Act: -0.0001

Data Index: 941065 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.8620. Min Act: -0.0001

Data Index: 450256 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1275198 (C4 (Web Text))

Max Activating Token Index: 887