Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2479 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.8937. Min Act: -0.0000

Data Index: 571912 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.8226. Min Act: -0.0000

Data Index: 851239 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.4335. Min Act: -0.0000

Data Index: 457273 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.2656. Min Act: -0.0000

Data Index: 67917 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.1942. Min Act: -0.0000

Data Index: 179429 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.2107. Min Act: -0.0000

Data Index: 89903 (C4 (Web Text))

Max Activating Token Index: 606

Text #6

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.2054. Min Act: -0.0000

Data Index: 255451 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1003174 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.0942. Min Act: -0.0000

Data Index: 751379 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.1479. Min Act: -0.0000

Data Index: 6562 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.1440. Min Act: -0.0000

Data Index: 744121 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.1276. Min Act: -0.0000

Data Index: 994065 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.1907. Min Act: -0.0000

Data Index: 398573 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.1088. Min Act: -0.0000

Data Index: 791277 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.0888. Min Act: -0.0000

Data Index: 557573 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.0757. Min Act: -0.0000

Data Index: 1042438 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.1415. Min Act: -0.0000

Data Index: 397314 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.0153. Min Act: -0.0000

Data Index: 717579 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.8937. Min Range: -1.8937

Max Act: 0.9733. Min Act: -0.0000

Data Index: 91675 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.8937. Min Range: -1.8937

Max Act: 1.0804. Min Act: -0.0000

Data Index: 769742 (C4 (Web Text))

Max Activating Token Index: 986