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

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

Neuron 2382 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: 1.6171. Min Range: -1.6171

Max Act: 1.5827. Min Act: -0.0001

Data Index: 513207 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.4549. Min Act: -0.0001

Data Index: 1129812 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.6132. Min Act: -0.0001

Data Index: 692753 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.6171. Min Act: -0.0001

Data Index: 576430 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.4683. Min Act: -0.0001

Data Index: 1224289 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.4632. Min Act: -0.0001

Data Index: 1350720 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3874. Min Act: -0.0001

Data Index: 1106496 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.4402. Min Act: -0.0001

Data Index: 1127353 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.4072. Min Act: -0.0001

Data Index: 296616 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3944. Min Act: -0.0001

Data Index: 896523 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3807. Min Act: -0.0001

Data Index: 632526 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3719. Min Act: -0.0001

Data Index: 1051046 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3329. Min Act: -0.0001

Data Index: 713791 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3860. Min Act: -0.0001

Data Index: 1476135 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.2378. Min Act: -0.0001

Data Index: 567869 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3049. Min Act: -0.0001

Data Index: 64850 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.3369. Min Act: -0.0001

Data Index: 999902 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.1876. Min Act: -0.0001

Data Index: 109778 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.2778. Min Act: -0.0001

Data Index: 85058 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.6171. Min Range: -1.6171

Max Act: 1.2471. Min Act: -0.0001

Data Index: 852550 (C4 (Web Text))

Max Activating Token Index: 251