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

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

Neuron 5547 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.9419. Min Act: -0.0002

Data Index: 623153 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8736. Min Act: -0.0002

Data Index: 899118 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8731. Min Act: -0.0002

Data Index: 1115846 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8486. Min Act: -0.0002

Data Index: 310685 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8382. Min Act: -0.0002

Data Index: 182190 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8194. Min Act: -0.0003

Data Index: 953791 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8407. Min Act: -0.0002

Data Index: 1164490 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8435. Min Act: -0.0002

Data Index: 178147 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8177. Min Act: -0.0002

Data Index: 277953 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8090. Min Act: -0.0002

Data Index: 576188 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8090. Min Act: -0.0002

Data Index: 508403 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8014. Min Act: -0.0002

Data Index: 1004606 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.8172. Min Act: -0.0002

Data Index: 242980 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.7929. Min Act: -0.0003

Data Index: 1273385 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.7953. Min Act: -0.0002

Data Index: 1333505 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.7918. Min Act: -0.0002

Data Index: 1277359 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.7727. Min Act: -0.0002

Data Index: 61053 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.7838. Min Act: -0.0002

Data Index: 955788 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.7658. Min Act: -0.0003

Data Index: 1038162 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.9419. Min Range: -0.9419

Max Act: 0.7668. Min Act: -0.0002

Data Index: 6656 (C4 (Web Text))

Max Activating Token Index: 476