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

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

Neuron 3648 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: 5.9012. Min Range: -5.9012

Max Act: 5.9012. Min Act: -0.0000

Data Index: 856470 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 5.9012. Min Range: -5.9012

Max Act: 5.7548. Min Act: -0.0000

Data Index: 691836 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 5.9012. Min Range: -5.9012

Max Act: 5.2046. Min Act: 0.0000

Data Index: 1025984 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.9077. Min Act: -0.0000

Data Index: 634546 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.8180. Min Act: -0.0000

Data Index: 665115 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.8142. Min Act: -0.0000

Data Index: 491342 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.4014. Min Act: -0.0000

Data Index: 948388 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.5512. Min Act: -0.0000

Data Index: 1025373 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.5383. Min Act: -0.0000

Data Index: 1351145 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.4921. Min Act: -0.0000

Data Index: 558506 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.1898. Min Act: -0.0000

Data Index: 490095 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.3109. Min Act: -0.0000

Data Index: 959930 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.1405. Min Act: -0.0000

Data Index: 371133 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.4958. Min Act: -0.0000

Data Index: 377698 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.2460. Min Act: -0.0000

Data Index: 742103 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.0044. Min Act: -0.0000

Data Index: 1270668 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 5.9012. Min Range: -5.9012

Max Act: 3.9608. Min Act: -0.0000

Data Index: 640611 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.2972. Min Act: -0.0000

Data Index: 516677 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.0991. Min Act: -0.0000

Data Index: 1190163 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 5.9012. Min Range: -5.9012

Max Act: 4.2763. Min Act: -0.0000

Data Index: 716676 (C4 (Web Text))

Max Activating Token Index: 372