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

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

Neuron 3551 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.7980. Min Act: -0.0001

Data Index: 967583 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6781. Min Act: -0.0001

Data Index: 1198596 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6243. Min Act: -0.0001

Data Index: 628378 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6171. Min Act: -0.0001

Data Index: 367018 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5977. Min Act: -0.0001

Data Index: 256934 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6337. Min Act: -0.0001

Data Index: 870366 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6132. Min Act: -0.0001

Data Index: 691968 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6029. Min Act: -0.0001

Data Index: 413612 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5976. Min Act: -0.0001

Data Index: 1207537 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6008. Min Act: -0.0001

Data Index: 166367 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5949. Min Act: -0.0001

Data Index: 306233 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5690. Min Act: -0.0001

Data Index: 1345396 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5646. Min Act: -0.0001

Data Index: 257097 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5848. Min Act: -0.0001

Data Index: 445068 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5691. Min Act: -0.0001

Data Index: 476039 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6013. Min Act: -0.0001

Data Index: 742306 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.6105. Min Act: -0.0001

Data Index: 1139089 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5897. Min Act: -0.0001

Data Index: 239263 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5501. Min Act: -0.0001

Data Index: 208078 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.7980. Min Range: -0.7980

Max Act: 0.5669. Min Act: -0.0001

Data Index: 273013 (C4 (Web Text))

Max Activating Token Index: 763