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

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

Neuron 2014 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0636. Min Act: -0.0001

Data Index: 89708 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0558. Min Act: -0.0001

Data Index: 837680 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1034248 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1082728 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0549. Min Act: -0.0001

Data Index: 742996 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0593. Min Act: -0.0001

Data Index: 497417 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0494. Min Act: -0.0001

Data Index: 34310 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0547. Min Act: -0.0001

Data Index: 822518 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0475. Min Act: -0.0001

Data Index: 605482 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0522. Min Act: -0.0001

Data Index: 411481 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0530. Min Act: -0.0001

Data Index: 195271 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0489. Min Act: -0.0001

Data Index: 245101 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0507. Min Act: -0.0001

Data Index: 63450 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1202829 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0489. Min Act: -0.0001

Data Index: 855202 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0486. Min Act: -0.0001

Data Index: 360453 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0503. Min Act: -0.0001

Data Index: 450277 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1216032 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0499. Min Act: -0.0001

Data Index: 170171 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0636. Min Range: -0.0636

Max Act: 0.0516. Min Act: -0.0001

Data Index: 146457 (C4 (Web Text))

Max Activating Token Index: 171