Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2673 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5873. Min Act: -0.0001

Data Index: 927014 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5316. Min Act: -0.0001

Data Index: 67576 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5403. Min Act: -0.0001

Data Index: 100756 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5944. Min Act: -0.0001

Data Index: 329386 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5424. Min Act: -0.0001

Data Index: 139853 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5802. Min Act: -0.0001

Data Index: 130447 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5975. Min Act: -0.0001

Data Index: 788405 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5885. Min Act: -0.0001

Data Index: 570051 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5840. Min Act: -0.0001

Data Index: 628425 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5630. Min Act: -0.0001

Data Index: 1048260 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5570. Min Act: -0.0001

Data Index: 801617 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5981. Min Act: -0.0001

Data Index: 114520 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5582. Min Act: -0.0001

Data Index: 1069754 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5353. Min Act: -0.0001

Data Index: 286326 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5727. Min Act: -0.0001

Data Index: 238109 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5339. Min Act: -0.0001

Data Index: 1181097 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5675. Min Act: -0.0001

Data Index: 349094 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5498. Min Act: -0.0001

Data Index: 1044167 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5458. Min Act: -0.0001

Data Index: 467004 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.5981. Min Range: -0.5981

Max Act: 0.5432. Min Act: -0.0001

Data Index: 386482 (C4 (Web Text))

Max Activating Token Index: 693