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

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

Neuron 3318 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4462. Min Range: -3.4462

Max Act: 3.4462. Min Act: -0.0000

Data Index: 260787 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.7074. Min Act: -0.0000

Data Index: 222688 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.6454. Min Act: -0.0000

Data Index: 984922 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.7681. Min Act: -0.0000

Data Index: 1275376 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.7547. Min Act: -0.0000

Data Index: 882977 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.6292. Min Act: -0.0000

Data Index: 21392 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.4827. Min Act: -0.0000

Data Index: 1226795 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.5928. Min Act: -0.0000

Data Index: 725869 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.3541. Min Act: -0.0000

Data Index: 512703 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.4178. Min Act: -0.0000

Data Index: 406618 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.2936. Min Act: -0.0000

Data Index: 1259251 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.2664. Min Act: -0.0000

Data Index: 425647 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.2630. Min Act: -0.0000

Data Index: 362281 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.4803. Min Act: -0.0000

Data Index: 1245255 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.2378. Min Act: -0.0000

Data Index: 901537 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.2004. Min Act: -0.0000

Data Index: 504829 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.1834. Min Act: -0.0000

Data Index: 1069014 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.0123. Min Act: -0.0000

Data Index: 509306 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.1296. Min Act: -0.0000

Data Index: 1182973 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 3.4462. Min Range: -3.4462

Max Act: 2.1123. Min Act: -0.0000

Data Index: 428527 (C4 (Web Text))

Max Activating Token Index: 464