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

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

Neuron 572 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.0793. Min Act: -0.0001

Data Index: 1316700 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9882. Min Act: -0.0001

Data Index: 893115 (C4 (Web Text))

Max Activating Token Index: 934

Text #2

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.0279. Min Act: -0.0000

Data Index: 976977 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.0535. Min Act: -0.0001

Data Index: 648722 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.0949. Min Act: -0.0001

Data Index: 833210 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.1146. Min Act: -0.0001

Data Index: 470292 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9756. Min Act: -0.0001

Data Index: 486965 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.1294. Min Act: -0.0001

Data Index: 421010 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.0315. Min Act: -0.0001

Data Index: 571675 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9046. Min Act: -0.0001

Data Index: 367050 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9127. Min Act: -0.0000

Data Index: 717515 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.0751. Min Act: -0.0001

Data Index: 203674 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.0242. Min Act: -0.0001

Data Index: 1089177 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9008. Min Act: -0.0001

Data Index: 1181031 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9590. Min Act: -0.0001

Data Index: 412102 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.8902. Min Act: -0.0001

Data Index: 610350 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9097. Min Act: -0.0001

Data Index: 919480 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.0375. Min Act: -0.0001

Data Index: 38818 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 1.1294. Min Range: -1.1294

Max Act: 0.9915. Min Act: -0.0001

Data Index: 1016307 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 1.1294. Min Range: -1.1294

Max Act: 1.0085. Min Act: -0.0001

Data Index: 116764 (C4 (Web Text))

Max Activating Token Index: 664