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

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

Neuron 735 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7022. Min Act: -0.0001

Data Index: 943587 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.8725. Min Act: -0.0001

Data Index: 202166 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.8395. Min Act: -0.0001

Data Index: 1173416 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7049. Min Act: -0.0001

Data Index: 943113 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7089. Min Act: -0.0001

Data Index: 1347777 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6437. Min Act: -0.0001

Data Index: 1202749 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7068. Min Act: -0.0000

Data Index: 414095 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6176. Min Act: -0.0000

Data Index: 957235 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6898. Min Act: -0.0000

Data Index: 413010 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1060736 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6037. Min Act: -0.0000

Data Index: 15505 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.5937. Min Act: -0.0000

Data Index: 537517 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1346838 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.4815. Min Act: -0.0001

Data Index: 303218 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6231. Min Act: -0.0001

Data Index: 392937 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6218. Min Act: -0.0001

Data Index: 477857 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.4889. Min Act: -0.0001

Data Index: 646583 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.5955. Min Act: -0.0001

Data Index: 185531 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.5634. Min Act: -0.0001

Data Index: 903549 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6361. Min Act: -0.0001

Data Index: 492971 (C4 (Web Text))

Max Activating Token Index: 451