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

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

Neuron 3517 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: 3.2005. Min Range: -3.2005

Max Act: 3.2005. Min Act: -0.0000

Data Index: 113439 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 3.2005. Min Range: -3.2005

Max Act: 3.0778. Min Act: -0.0000

Data Index: 426846 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 3.2005. Min Range: -3.2005

Max Act: 3.1437. Min Act: -0.0000

Data Index: 507956 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.8338. Min Act: -0.0000

Data Index: 1326342 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 3.2005. Min Range: -3.2005

Max Act: 3.1016. Min Act: -0.0000

Data Index: 442305 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.8057. Min Act: -0.0001

Data Index: 46010 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.7852. Min Act: -0.0001

Data Index: 216358 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.5774. Min Act: -0.0000

Data Index: 864074 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.6101. Min Act: -0.0000

Data Index: 942663 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.7219. Min Act: -0.0001

Data Index: 463937 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.5343. Min Act: -0.0001

Data Index: 481925 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.7469. Min Act: -0.0000

Data Index: 1341382 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.7385. Min Act: -0.0001

Data Index: 531168 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.4561. Min Act: -0.0000

Data Index: 1282494 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.5958. Min Act: -0.0000

Data Index: 254694 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.5962. Min Act: -0.0000

Data Index: 713633 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.5773. Min Act: -0.0000

Data Index: 309346 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.8375. Min Act: -0.0000

Data Index: 1205562 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.5579. Min Act: -0.0000

Data Index: 440010 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 3.2005. Min Range: -3.2005

Max Act: 2.6003. Min Act: -0.0000

Data Index: 1307574 (C4 (Web Text))

Max Activating Token Index: 702