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

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

Neuron 3714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7938. Min Act: -0.0001

Data Index: 233148 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.8076. Min Act: -0.0001

Data Index: 454607 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.8235. Min Act: -0.0001

Data Index: 948920 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7851. Min Act: -0.0001

Data Index: 18715 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1193478 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6867. Min Act: -0.0001

Data Index: 341620 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6308. Min Act: -0.0001

Data Index: 557481 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6798. Min Act: -0.0001

Data Index: 581995 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.7122. Min Act: -0.0001

Data Index: 346533 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6699. Min Act: -0.0001

Data Index: 1313253 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6673. Min Act: -0.0001

Data Index: 540830 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6995. Min Act: -0.0001

Data Index: 80443 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6323. Min Act: -0.0001

Data Index: 254308 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6928. Min Act: -0.0001

Data Index: 939067 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6897. Min Act: -0.0001

Data Index: 728263 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6607. Min Act: -0.0001

Data Index: 1287746 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6441. Min Act: -0.0001

Data Index: 1096608 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6536. Min Act: -0.0001

Data Index: 728512 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6112. Min Act: -0.0001

Data Index: 1006705 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.8235. Min Range: -0.8235

Max Act: 0.6131. Min Act: -0.0001

Data Index: 1062740 (C4 (Web Text))

Max Activating Token Index: 265