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

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

Neuron 4369 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: 0.1449. Min Range: -0.1449

Max Act: 0.1449. Min Act: -0.0000

Data Index: 991523 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1178. Min Act: -0.0000

Data Index: 281111 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1183023 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1421627 (Python Code)

Max Activating Token Index: 242

Text #4

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1106. Min Act: -0.0000

Data Index: 126263 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1097. Min Act: -0.0000

Data Index: 65701 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1076. Min Act: -0.0000

Data Index: 586915 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1097. Min Act: -0.0000

Data Index: 616507 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1050. Min Act: -0.0000

Data Index: 138638 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.1014. Min Act: -0.0000

Data Index: 88312 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1486642 (Python Code)

Max Activating Token Index: 995

Text #11

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1474014 (Python Code)

Max Activating Token Index: 161

Text #12

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0971. Min Act: -0.0000

Data Index: 485040 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1282027 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0846. Min Act: -0.0000

Data Index: 528843 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0896. Min Act: -0.0000

Data Index: 879318 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1105820 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0885. Min Act: -0.0000

Data Index: 312865 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0913. Min Act: -0.0000

Data Index: 1211192 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.1449. Min Range: -0.1449

Max Act: 0.0938. Min Act: -0.0000

Data Index: 475703 (C4 (Web Text))

Max Activating Token Index: 282