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

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

Neuron 1622 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7058. Min Act: -0.0004

Data Index: 793497 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7124. Min Act: -0.0004

Data Index: 5933 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5977. Min Act: -0.0004

Data Index: 184106 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6716. Min Act: -0.0004

Data Index: 958028 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7141. Min Act: -0.0004

Data Index: 1029791 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6432. Min Act: -0.0004

Data Index: 1026457 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6951. Min Act: -0.0004

Data Index: 866754 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6087. Min Act: -0.0004

Data Index: 716763 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5682. Min Act: -0.0004

Data Index: 667813 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6447. Min Act: -0.0004

Data Index: 15689 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5803. Min Act: -0.0004

Data Index: 185219 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6620. Min Act: -0.0004

Data Index: 181159 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7036. Min Act: -0.0004

Data Index: 960721 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7680. Min Act: -0.0004

Data Index: 363472 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5944. Min Act: -0.0004

Data Index: 587719 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6300. Min Act: -0.0004

Data Index: 891766 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.7118. Min Act: -0.0004

Data Index: 153977 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5852. Min Act: -0.0004

Data Index: 777687 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.5315. Min Act: -0.0004

Data Index: 552837 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 0.7680. Min Range: -0.7680

Max Act: 0.6247. Min Act: -0.0004

Data Index: 524411 (C4 (Web Text))

Max Activating Token Index: 64