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

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

Neuron 4657 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.3102. Min Act: -0.0001

Data Index: 674423 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.3102. Min Act: -0.0001

Data Index: 165841 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.3032. Min Act: -0.0001

Data Index: 1233717 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2926. Min Act: -0.0001

Data Index: 495901 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2893. Min Act: -0.0001

Data Index: 207601 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2849. Min Act: -0.0001

Data Index: 1190800 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2809. Min Act: -0.0001

Data Index: 942793 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2809. Min Act: -0.0001

Data Index: 766377 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2699. Min Act: -0.0001

Data Index: 754453 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2705. Min Act: -0.0001

Data Index: 488552 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2768. Min Act: -0.0001

Data Index: 1221078 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2739. Min Act: -0.0001

Data Index: 1119683 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2694. Min Act: -0.0001

Data Index: 1251044 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2680. Min Act: -0.0001

Data Index: 254157 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2703. Min Act: -0.0001

Data Index: 881805 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2694. Min Act: -0.0001

Data Index: 686177 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2638. Min Act: -0.0001

Data Index: 822581 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2656. Min Act: -0.0001

Data Index: 451858 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2618. Min Act: -0.0001

Data Index: 811822 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2695. Min Act: -0.0001

Data Index: 848446 (C4 (Web Text))

Max Activating Token Index: 777