Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1554 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0727. Min Range: -1.0727

Max Act: 1.0727. Min Act: -0.0001

Data Index: 768354 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 1.0727. Min Range: -1.0727

Max Act: 1.0412. Min Act: -0.0001

Data Index: 124700 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.9931. Min Act: -0.0001

Data Index: 1326173 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.9618. Min Act: -0.0001

Data Index: 466882 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.9610. Min Act: -0.0001

Data Index: 437848 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.9046. Min Act: -0.0001

Data Index: 947527 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.9237. Min Act: -0.0001

Data Index: 1104158 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.9255. Min Act: -0.0001

Data Index: 881869 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.8749. Min Act: -0.0001

Data Index: 1093037 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.7198. Min Act: -0.0001

Data Index: 606540 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.8982. Min Act: -0.0001

Data Index: 468015 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.9180. Min Act: -0.0001

Data Index: 875833 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.8816. Min Act: -0.0001

Data Index: 320736 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.8099. Min Act: -0.0001

Data Index: 119793 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.9057. Min Act: -0.0001

Data Index: 12724 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.8263. Min Act: -0.0001

Data Index: 400420 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.8674. Min Act: -0.0001

Data Index: 1019061 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.7868. Min Act: -0.0001

Data Index: 259543 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.7541. Min Act: -0.0001

Data Index: 1017735 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.0727. Min Range: -1.0727

Max Act: 0.7706. Min Act: -0.0001

Data Index: 29446 (C4 (Web Text))

Max Activating Token Index: 613