Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2573 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.2944. Min Act: -0.0001

Data Index: 145220 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9578. Min Act: -0.0001

Data Index: 882298 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0904. Min Act: -0.0001

Data Index: 100421 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9516. Min Act: -0.0001

Data Index: 970036 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9754. Min Act: -0.0001

Data Index: 102179 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9660. Min Act: -0.0001

Data Index: 870604 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9540. Min Act: -0.0001

Data Index: 1025037 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9487. Min Act: -0.0001

Data Index: 687219 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9473. Min Act: -0.0001

Data Index: 1250538 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8457. Min Act: -0.0001

Data Index: 502741 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.7400. Min Act: -0.0001

Data Index: 794437 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8940. Min Act: -0.0001

Data Index: 640203 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9549. Min Act: -0.0001

Data Index: 232427 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.9127. Min Act: -0.0001

Data Index: 409238 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.7936. Min Act: -0.0001

Data Index: 485804 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.7376. Min Act: -0.0001

Data Index: 447860 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.5377. Min Act: -0.0001

Data Index: 149937 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8692. Min Act: -0.0001

Data Index: 585652 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 1.2944. Min Range: -1.2944

Max Act: 0.8599. Min Act: -0.0001

Data Index: 123860 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 1.2944. Min Range: -1.2944

Max Act: 1.0085. Min Act: -0.0001

Data Index: 1098092 (C4 (Web Text))

Max Activating Token Index: 682