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

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

Neuron 3770 in Layer 1

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: 0.6755. Min Range: -0.6755

Max Act: 0.6755. Min Act: -0.0002

Data Index: 669859 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6639. Min Act: -0.0002

Data Index: 1021634 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6560. Min Act: -0.0002

Data Index: 53791 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6390. Min Act: -0.0002

Data Index: 646066 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6197. Min Act: -0.0002

Data Index: 244690 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6152. Min Act: -0.0002

Data Index: 170282 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6070. Min Act: -0.0002

Data Index: 1139566 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6088. Min Act: -0.0002

Data Index: 1176008 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6033. Min Act: -0.0002

Data Index: 1026848 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6044. Min Act: -0.0002

Data Index: 544894 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6033. Min Act: -0.0002

Data Index: 886135 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5938. Min Act: -0.0002

Data Index: 796386 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5856. Min Act: -0.0002

Data Index: 964896 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5877. Min Act: -0.0002

Data Index: 1147634 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5856. Min Act: -0.0002

Data Index: 835661 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.6015. Min Act: -0.0002

Data Index: 1151000 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5864. Min Act: -0.0002

Data Index: 1241427 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5911. Min Act: -0.0002

Data Index: 544606 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5917. Min Act: -0.0002

Data Index: 725152 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.6755. Min Range: -0.6755

Max Act: 0.5776. Min Act: -0.0002

Data Index: 1058702 (C4 (Web Text))

Max Activating Token Index: 93