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

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

Neuron 4622 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9549. Min Act: -0.0002

Data Index: 1124818 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9342. Min Act: -0.0002

Data Index: 1195071 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9375. Min Act: -0.0002

Data Index: 1266415 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9270. Min Act: -0.0002

Data Index: 976502 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9286. Min Act: -0.0002

Data Index: 1236593 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9063. Min Act: -0.0002

Data Index: 626403 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9133. Min Act: -0.0002

Data Index: 797859 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9175. Min Act: -0.0002

Data Index: 1304746 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8532. Min Act: -0.0003

Data Index: 66124 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8830. Min Act: -0.0002

Data Index: 1240476 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8679. Min Act: -0.0002

Data Index: 1060559 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8550. Min Act: -0.0002

Data Index: 774337 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7810. Min Act: -0.0002

Data Index: 680547 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8201. Min Act: -0.0002

Data Index: 948957 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8256. Min Act: -0.0002

Data Index: 891677 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9752. Min Act: -0.0002

Data Index: 1083893 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8148. Min Act: -0.0002

Data Index: 559058 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8390. Min Act: -0.0002

Data Index: 215636 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8580. Min Act: -0.0002

Data Index: 1138791 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8141. Min Act: -0.0002

Data Index: 633469 (C4 (Web Text))

Max Activating Token Index: 90