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

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

Neuron 2629 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.9940. Min Act: -0.0000

Data Index: 285161 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.5676. Min Act: -0.0000

Data Index: 5603 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.3032. Min Act: -0.0000

Data Index: 798569 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 6.1031. Min Range: -6.1031

Max Act: 6.1031. Min Act: -0.0000

Data Index: 1019881 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.4869. Min Act: -0.0000

Data Index: 166987 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.8725. Min Act: -0.0000

Data Index: 1247473 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.8349. Min Act: -0.0000

Data Index: 135011 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.6206. Min Act: -0.0000

Data Index: 956492 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.5646. Min Act: -0.0000

Data Index: 279325 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.7363. Min Act: -0.0000

Data Index: 714619 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.5163. Min Act: -0.0000

Data Index: 508895 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.0691. Min Act: -0.0000

Data Index: 215629 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.6159. Min Act: -0.0000

Data Index: 52257 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.4281. Min Act: -0.0000

Data Index: 374538 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.4261. Min Act: -0.0000

Data Index: 861230 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.3886. Min Act: -0.0000

Data Index: 1025912 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.4438. Min Act: -0.0000

Data Index: 99643 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.0448. Min Act: -0.0000

Data Index: 705759 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.3810. Min Act: -0.0000

Data Index: 823571 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 6.1031. Min Range: -6.1031

Max Act: 5.2005. Min Act: -0.0000

Data Index: 180190 (C4 (Web Text))

Max Activating Token Index: 63