Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 247 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.9091. Min Act: -0.0000

Data Index: 909102 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7207. Min Act: -0.0000

Data Index: 499318 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7073. Min Act: -0.0000

Data Index: 822304 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7216. Min Act: -0.0001

Data Index: 1049958 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6469. Min Act: -0.0000

Data Index: 509970 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6673. Min Act: -0.0000

Data Index: 172410 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6289. Min Act: -0.0001

Data Index: 680910 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6405. Min Act: -0.0000

Data Index: 949633 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6314. Min Act: -0.0000

Data Index: 553685 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1030788 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1352123 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5950. Min Act: -0.0000

Data Index: 981310 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1018414 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6274. Min Act: -0.0000

Data Index: 840420 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6324. Min Act: -0.0000

Data Index: 30698 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6006. Min Act: -0.0000

Data Index: 917970 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5419. Min Act: -0.0000

Data Index: 5177 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5735. Min Act: -0.0001

Data Index: 1098502 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1195527 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5839. Min Act: -0.0000

Data Index: 324115 (C4 (Web Text))

Max Activating Token Index: 874