Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1644 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.1060. Min Act: -0.0001

Data Index: 650528 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0444. Min Act: -0.0001

Data Index: 1093921 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9866. Min Act: -0.0001

Data Index: 903069 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0575. Min Act: -0.0001

Data Index: 952458 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0494. Min Act: -0.0001

Data Index: 498808 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9964. Min Act: -0.0001

Data Index: 699620 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0116. Min Act: -0.0001

Data Index: 525905 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0124. Min Act: -0.0001

Data Index: 133730 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9712. Min Act: -0.0001

Data Index: 1066782 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9846. Min Act: -0.0001

Data Index: 229275 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0019. Min Act: -0.0001

Data Index: 356319 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9906. Min Act: -0.0001

Data Index: 1272727 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0241. Min Act: -0.0001

Data Index: 370378 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9833. Min Act: -0.0001

Data Index: 332777 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9606. Min Act: -0.0001

Data Index: 990795 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9315. Min Act: -0.0001

Data Index: 72869 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9010. Min Act: -0.0001

Data Index: 1231153 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9779. Min Act: -0.0001

Data Index: 1071574 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8964. Min Act: -0.0001

Data Index: 266619 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9388. Min Act: -0.0001

Data Index: 890613 (C4 (Web Text))

Max Activating Token Index: 999