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

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

Neuron 723 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.9104. Min Act: -0.0001

Data Index: 894629 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.7601. Min Act: -0.0001

Data Index: 674069 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.8119. Min Act: -0.0001

Data Index: 104323 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.7863. Min Act: -0.0001

Data Index: 4714 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.6902. Min Act: -0.0001

Data Index: 187383 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.6951. Min Act: -0.0001

Data Index: 412227 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.6662. Min Act: -0.0001

Data Index: 73837 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.7718. Min Act: -0.0001

Data Index: 90395 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.6939. Min Act: -0.0001

Data Index: 677964 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1318006 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.7827. Min Act: -0.0001

Data Index: 1007181 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.7416. Min Act: -0.0001

Data Index: 579966 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.6399. Min Act: -0.0001

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.6735. Min Act: -0.0001

Data Index: 905488 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.7169. Min Act: -0.0001

Data Index: 1202182 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.7304. Min Act: -0.0001

Data Index: 1071603 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.6764. Min Act: -0.0001

Data Index: 795510 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.5726. Min Act: -0.0001

Data Index: 1285060 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.6947. Min Act: -0.0001

Data Index: 1028847 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.9104. Min Range: -0.9104

Max Act: 0.6640. Min Act: -0.0001

Data Index: 643669 (C4 (Web Text))

Max Activating Token Index: 826