Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4291 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1267. Min Act: -0.0001

Data Index: 120744 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1245. Min Act: -0.0001

Data Index: 982951 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1139. Min Act: -0.0001

Data Index: 552879 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1069. Min Act: -0.0001

Data Index: 757721 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1031. Min Act: -0.0001

Data Index: 1465097 (Python Code)

Max Activating Token Index: 514

Text #5

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1079. Min Act: -0.0001

Data Index: 161432 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0968. Min Act: -0.0001

Data Index: 940145 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1027. Min Act: -0.0001

Data Index: 324811 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1018. Min Act: -0.0001

Data Index: 954355 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0966. Min Act: -0.0001

Data Index: 973241 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0996. Min Act: -0.0001

Data Index: 4709 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0950. Min Act: -0.0001

Data Index: 19912 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0828. Min Act: -0.0001

Data Index: 744345 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1529422 (Python Code)

Max Activating Token Index: 895

Text #14

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0947. Min Act: -0.0001

Data Index: 804754 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1542186 (Python Code)

Max Activating Token Index: 99

Text #16

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0910. Min Act: -0.0001

Data Index: 986127 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1225360 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0843. Min Act: -0.0001

Data Index: 546545 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0853. Min Act: -0.0001

Data Index: 454053 (C4 (Web Text))

Max Activating Token Index: 617