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

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

Neuron 5309 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.7117. Min Act: -0.0000

Data Index: 974857 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.3568. Min Act: -0.0000

Data Index: 745642 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.4441. Min Act: -0.0000

Data Index: 794738 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.2549. Min Act: -0.0000

Data Index: 869819 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.2591. Min Act: -0.0000

Data Index: 1079774 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1031756 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.1294. Min Act: -0.0000

Data Index: 835487 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.2032. Min Act: -0.0000

Data Index: 873841 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1281319 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.1745. Min Act: -0.0000

Data Index: 187270 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.1273. Min Act: -0.0000

Data Index: 766954 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1162748 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.1391. Min Act: -0.0000

Data Index: 210417 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1057981 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0482. Min Act: -0.0000

Data Index: 655757 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0607. Min Act: -0.0000

Data Index: 244936 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1046631 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.7117. Min Range: -1.7117

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1457329 (Python Code)

Max Activating Token Index: 190

Text #18

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0108. Min Act: -0.0000

Data Index: 874765 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.7117. Min Range: -1.7117

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1037431 (C4 (Web Text))

Max Activating Token Index: 114