Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1057 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0129. Min Act: -0.0004

Data Index: 399340 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0129. Min Act: -0.0004

Data Index: 487638 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0128. Min Act: -0.0004

Data Index: 931236 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0125. Min Act: -0.0004

Data Index: 54840 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0125. Min Act: -0.0004

Data Index: 878639 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0125. Min Act: -0.0005

Data Index: 650954 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0125. Min Act: -0.0004

Data Index: 325282 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1246422 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0124. Min Act: -0.0005

Data Index: 376749 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0124. Min Act: -0.0004

Data Index: 96712 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0123. Min Act: -0.0005

Data Index: 868156 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0123. Min Act: -0.0004

Data Index: 1261366 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0122. Min Act: -0.0004

Data Index: 1282163 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0122. Min Act: -0.0004

Data Index: 605075 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0123. Min Act: -0.0004

Data Index: 648587 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0120. Min Act: -0.0004

Data Index: 355469 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0122. Min Act: -0.0005

Data Index: 439542 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0121. Min Act: -0.0004

Data Index: 446839 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0122. Min Act: -0.0004

Data Index: 638234 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.0129. Min Range: -0.0129

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1237842 (C4 (Web Text))

Max Activating Token Index: 718