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

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

Neuron 4159 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.4203. Min Act: -0.0000

Data Index: 833240 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.4016. Min Act: -0.0000

Data Index: 850103 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3561. Min Act: -0.0000

Data Index: 945241 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1034740 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3366. Min Act: -0.0000

Data Index: 1040453 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3533. Min Act: -0.0000

Data Index: 724149 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1363978 (Python Code)

Max Activating Token Index: 508

Text #7

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3083. Min Act: -0.0000

Data Index: 333097 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1232075 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3180. Min Act: -0.0000

Data Index: 918940 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3323. Min Act: -0.0000

Data Index: 200623 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3202. Min Act: -0.0000

Data Index: 155445 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3066. Min Act: -0.0000

Data Index: 758675 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1267876 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3059. Min Act: -0.0000

Data Index: 560329 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3058. Min Act: -0.0000

Data Index: 882773 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.2738. Min Act: -0.0000

Data Index: 811207 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3092. Min Act: -0.0000

Data Index: 19400 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.2941. Min Act: -0.0000

Data Index: 634988 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.4203. Min Range: -0.4203

Max Act: 0.3011. Min Act: -0.0000

Data Index: 811925 (C4 (Web Text))

Max Activating Token Index: 760