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

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

Neuron 21 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: 1.7077. Min Range: -1.7077

Max Act: 1.7077. Min Act: -0.0002

Data Index: 102997 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.5670. Min Act: -0.0002

Data Index: 1236639 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.5288. Min Act: -0.0002

Data Index: 1357572 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.5185. Min Act: -0.0002

Data Index: 589706 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.4823. Min Act: -0.0002

Data Index: 1218404 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.4556. Min Act: -0.0002

Data Index: 250931 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.4326. Min Act: -0.0002

Data Index: 551420 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.4810. Min Act: -0.0002

Data Index: 805437 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.4190. Min Act: -0.0002

Data Index: 554018 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3934. Min Act: -0.0002

Data Index: 1126227 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3976. Min Act: -0.0002

Data Index: 808797 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3789. Min Act: -0.0002

Data Index: 194291 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3764. Min Act: -0.0002

Data Index: 998041 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3829. Min Act: -0.0002

Data Index: 994036 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3889. Min Act: -0.0002

Data Index: 899552 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3730. Min Act: -0.0002

Data Index: 348132 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3639. Min Act: -0.0002

Data Index: 505395 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3558. Min Act: -0.0002

Data Index: 707513 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3794. Min Act: -0.0002

Data Index: 871265 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 1.7077. Min Range: -1.7077

Max Act: 1.3678. Min Act: -0.0002

Data Index: 997597 (C4 (Web Text))

Max Activating Token Index: 21