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

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

Neuron 2110 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8923. Min Act: -0.0000

Data Index: 75195 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8786. Min Act: -0.0001

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.9230. Min Act: -0.0000

Data Index: 82090 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8569. Min Act: -0.0000

Data Index: 859454 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7686. Min Act: -0.0000

Data Index: 99850 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8305. Min Act: -0.0001

Data Index: 1357009 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7694. Min Act: -0.0000

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7357. Min Act: -0.0001

Data Index: 397184 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7525. Min Act: -0.0000

Data Index: 995521 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7261. Min Act: -0.0000

Data Index: 177894 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7083. Min Act: -0.0001

Data Index: 88919 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7357. Min Act: -0.0000

Data Index: 824864 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6799. Min Act: -0.0000

Data Index: 65843 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6654. Min Act: -0.0001

Data Index: 1082743 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1046931 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6436. Min Act: -0.0000

Data Index: 210557 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6167. Min Act: -0.0000

Data Index: 885590 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6794. Min Act: -0.0000

Data Index: 114182 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1028748 (C4 (Web Text))

Max Activating Token Index: 122