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

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

Neuron 1222 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.7006. Min Act: -0.0001

Data Index: 1150167 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6988. Min Act: -0.0001

Data Index: 1309508 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.7047. Min Act: -0.0001

Data Index: 894018 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6851. Min Act: -0.0001

Data Index: 1103397 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6589. Min Act: -0.0001

Data Index: 924123 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6374. Min Act: -0.0001

Data Index: 426206 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6509. Min Act: -0.0001

Data Index: 192691 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6155. Min Act: -0.0001

Data Index: 534274 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.5975. Min Act: -0.0001

Data Index: 242838 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6174. Min Act: -0.0001

Data Index: 289834 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.5900. Min Act: -0.0001

Data Index: 12537 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6207. Min Act: -0.0001

Data Index: 234779 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6056. Min Act: -0.0001

Data Index: 32698 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.5984. Min Act: -0.0001

Data Index: 70093 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.5670. Min Act: -0.0001

Data Index: 774636 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6105. Min Act: -0.0001

Data Index: 851326 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.5948. Min Act: -0.0001

Data Index: 366899 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.6003. Min Act: -0.0001

Data Index: 239967 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.5826. Min Act: -0.0001

Data Index: 768873 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.7047. Min Range: -0.7047

Max Act: 0.5794. Min Act: -0.0001

Data Index: 1142590 (C4 (Web Text))

Max Activating Token Index: 498