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

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

Neuron 2144 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.4569. Min Act: -0.0000

Data Index: 981121 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3974. Min Act: -0.0000

Data Index: 328999 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3671. Min Act: -0.0000

Data Index: 642039 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3605. Min Act: -0.0000

Data Index: 213627 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3478. Min Act: -0.0000

Data Index: 762726 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3456. Min Act: -0.0000

Data Index: 681931 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3541. Min Act: 0.0000

Data Index: 1146362 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3556. Min Act: -0.0000

Data Index: 448185 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3260. Min Act: -0.0000

Data Index: 472476 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1179689 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1356980 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1067936 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1077881 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2841. Min Act: -0.0000

Data Index: 344462 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2781. Min Act: -0.0000

Data Index: 108607 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1440572 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2842. Min Act: -0.0000

Data Index: 169818 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2921. Min Act: -0.0000

Data Index: 218484 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1246108 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.4569. Min Range: -0.4569

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1472809 (Python Code)

Max Activating Token Index: 452