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

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

Neuron 1538 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: 2.1730. Min Range: -2.1730

Max Act: 2.1730. Min Act: -0.0003

Data Index: 353186 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0298. Min Act: -0.0003

Data Index: 1069032 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0312. Min Act: -0.0002

Data Index: 1341375 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.9900. Min Act: -0.0002

Data Index: 598577 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.9908. Min Act: -0.0002

Data Index: 426797 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 2.1730. Min Range: -2.1730

Max Act: 2.0013. Min Act: -0.0003

Data Index: 760154 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.9539. Min Act: -0.0002

Data Index: 1261851 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.9179. Min Act: -0.0002

Data Index: 71293 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.9556. Min Act: -0.0002

Data Index: 1264131 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8855. Min Act: -0.0002

Data Index: 1148740 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8957. Min Act: -0.0002

Data Index: 1181002 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8540. Min Act: -0.0002

Data Index: 582179 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.9082. Min Act: -0.0002

Data Index: 431754 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8526. Min Act: -0.0002

Data Index: 596297 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8682. Min Act: -0.0002

Data Index: 707092 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8850. Min Act: -0.0003

Data Index: 1269976 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8314. Min Act: -0.0002

Data Index: 63430 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8210. Min Act: -0.0002

Data Index: 380276 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8555. Min Act: -0.0002

Data Index: 76634 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 2.1730. Min Range: -2.1730

Max Act: 1.8111. Min Act: -0.0002

Data Index: 761956 (C4 (Web Text))

Max Activating Token Index: 406