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

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

Neuron 1356 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6087. Min Range: -2.6087

Max Act: 2.6087. Min Act: -0.0000

Data Index: 499210 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 2.6087. Min Range: -2.6087

Max Act: 2.0185. Min Act: -0.0000

Data Index: 1264095 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.8970. Min Act: -0.0000

Data Index: 359960 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.8121. Min Act: -0.0000

Data Index: 114717 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.9077. Min Act: 0.0000

Data Index: 668560 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.6882. Min Act: -0.0000

Data Index: 516498 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.8266. Min Act: -0.0000

Data Index: 1113941 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.7091. Min Act: -0.0000

Data Index: 1069826 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.7987. Min Act: -0.0000

Data Index: 194448 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.7003. Min Act: -0.0000

Data Index: 449383 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.6944. Min Act: -0.0000

Data Index: 837377 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.6913. Min Act: -0.0000

Data Index: 962432 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1246783 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.6386. Min Act: -0.0000

Data Index: 399143 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.6246. Min Act: -0.0000

Data Index: 1225623 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.6124. Min Act: 0.0000

Data Index: 65222 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.6101. Min Act: -0.0000

Data Index: 568992 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.7263. Min Act: -0.0000

Data Index: 899516 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.6065. Min Act: -0.0000

Data Index: 701731 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 2.6087. Min Range: -2.6087

Max Act: 1.5892. Min Act: -0.0000

Data Index: 1061965 (C4 (Web Text))

Max Activating Token Index: 94