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

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

Neuron 879 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.8032. Min Act: -0.0001

Data Index: 870823 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6407. Min Act: -0.0001

Data Index: 378682 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.7328. Min Act: -0.0001

Data Index: 1064377 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6674. Min Act: -0.0001

Data Index: 1056987 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6403. Min Act: -0.0001

Data Index: 1196156 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6707. Min Act: -0.0001

Data Index: 467774 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6741. Min Act: -0.0001

Data Index: 597695 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6528. Min Act: -0.0001

Data Index: 1177366 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6451. Min Act: -0.0001

Data Index: 886985 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6013. Min Act: -0.0001

Data Index: 1109358 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6131. Min Act: -0.0001

Data Index: 460466 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6504. Min Act: -0.0001

Data Index: 942234 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5880. Min Act: -0.0001

Data Index: 417243 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6353. Min Act: -0.0001

Data Index: 685935 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6500. Min Act: -0.0001

Data Index: 371099 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5741. Min Act: -0.0001

Data Index: 43130 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6091. Min Act: -0.0001

Data Index: 1304753 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.6052. Min Act: -0.0001

Data Index: 568132 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5670. Min Act: -0.0001

Data Index: 1334504 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5780. Min Act: -0.0001

Data Index: 343041 (C4 (Web Text))

Max Activating Token Index: 374