Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3342 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.1083. Min Act: -0.0001

Data Index: 816978 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.1211. Min Act: -0.0001

Data Index: 643105 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.1350. Min Act: -0.0002

Data Index: 99611 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 1.1350. Min Range: -1.1350

Max Act: 1.0681. Min Act: -0.0002

Data Index: 836729 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9491. Min Act: -0.0002

Data Index: 57430 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9591. Min Act: -0.0002

Data Index: 554733 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9400. Min Act: -0.0001

Data Index: 216988 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9560. Min Act: -0.0001

Data Index: 1020494 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9579. Min Act: -0.0002

Data Index: 1176979 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9663. Min Act: -0.0001

Data Index: 1343493 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9285. Min Act: -0.0002

Data Index: 1323310 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9625. Min Act: -0.0002

Data Index: 653944 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9843. Min Act: -0.0002

Data Index: 1217812 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9214. Min Act: -0.0001

Data Index: 259314 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8850. Min Act: -0.0001

Data Index: 1237407 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9097. Min Act: -0.0001

Data Index: 1052768 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8923. Min Act: -0.0002

Data Index: 1089720 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8648. Min Act: -0.0001

Data Index: 1000238 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.9127. Min Act: -0.0002

Data Index: 328597 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 1.1350. Min Range: -1.1350

Max Act: 0.8790. Min Act: -0.0001

Data Index: 854019 (C4 (Web Text))

Max Activating Token Index: 161