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

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

Neuron 2257 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.5844. Min Act: -0.0002

Data Index: 91542 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.3545. Min Act: -0.0002

Data Index: 241097 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.3326. Min Act: -0.0001

Data Index: 714324 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.4263. Min Act: -0.0002

Data Index: 287161 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.2709. Min Act: -0.0001

Data Index: 703218 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.2845. Min Act: -0.0001

Data Index: 938499 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.2381. Min Act: -0.0001

Data Index: 440575 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.1913. Min Act: -0.0001

Data Index: 48573 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.2245. Min Act: -0.0001

Data Index: 1063419 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.1618. Min Act: -0.0001

Data Index: 688239 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.2396. Min Act: -0.0001

Data Index: 921893 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.2418. Min Act: -0.0002

Data Index: 897510 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.0616. Min Act: -0.0002

Data Index: 1032586 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.1424. Min Act: -0.0002

Data Index: 966600 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.1035. Min Act: -0.0002

Data Index: 1297530 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.1359. Min Act: -0.0002

Data Index: 747927 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.1353. Min Act: -0.0002

Data Index: 1192595 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.0095. Min Act: -0.0002

Data Index: 643941 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.1418. Min Act: -0.0001

Data Index: 833497 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 1.5844. Min Range: -1.5844

Max Act: 1.1497. Min Act: -0.0002

Data Index: 845284 (C4 (Web Text))

Max Activating Token Index: 416