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

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

Neuron 3155 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.9117. Min Act: -0.0001

Data Index: 651850 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.6823. Min Act: -0.0001

Data Index: 449038 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.6146. Min Act: -0.0001

Data Index: 534260 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.4555. Min Act: -0.0001

Data Index: 815439 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.4246. Min Act: -0.0001

Data Index: 902975 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.5246. Min Act: -0.0001

Data Index: 531232 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.5652. Min Act: -0.0001

Data Index: 1354049 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.4983. Min Act: -0.0001

Data Index: 844835 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.3605. Min Act: -0.0001

Data Index: 188432 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.3700. Min Act: -0.0001

Data Index: 1289591 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.2670. Min Act: -0.0001

Data Index: 1045461 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.1684. Min Act: -0.0001

Data Index: 924674 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.2568. Min Act: -0.0001

Data Index: 1334788 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.2950. Min Act: -0.0001

Data Index: 1333434 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.3386. Min Act: -0.0001

Data Index: 788142 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.3303. Min Act: -0.0001

Data Index: 890074 (C4 (Web Text))

Max Activating Token Index: 792

Text #16

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.3051. Min Act: -0.0001

Data Index: 451830 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.2219. Min Act: -0.0001

Data Index: 621897 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.2593. Min Act: -0.0001

Data Index: 193895 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 1.9117. Min Range: -1.9117

Max Act: 1.0757. Min Act: -0.0001

Data Index: 1398869 (Python Code)

Max Activating Token Index: 300