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

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

Neuron 1286 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: 2.7804. Min Range: -2.7804

Max Act: 2.7804. Min Act: -0.0002

Data Index: 67833 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.7413. Min Act: -0.0002

Data Index: 1176819 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.6881. Min Act: -0.0002

Data Index: 684279 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.6588. Min Act: -0.0002

Data Index: 720565 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.5429. Min Act: -0.0002

Data Index: 1144929 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.5726. Min Act: -0.0002

Data Index: 617918 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.6100. Min Act: -0.0002

Data Index: 762658 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.5471. Min Act: -0.0002

Data Index: 692788 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.4991. Min Act: -0.0002

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.5144. Min Act: -0.0002

Data Index: 480171 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.4567. Min Act: -0.0002

Data Index: 1216438 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.5077. Min Act: -0.0002

Data Index: 1227569 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.4373. Min Act: -0.0002

Data Index: 444716 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.4776. Min Act: -0.0002

Data Index: 603917 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.4184. Min Act: -0.0002

Data Index: 473990 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.4100. Min Act: -0.0002

Data Index: 1324091 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.4697. Min Act: -0.0002

Data Index: 1237442 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.3863. Min Act: -0.0002

Data Index: 621271 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.3309. Min Act: -0.0002

Data Index: 1241975 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 2.7804. Min Range: -2.7804

Max Act: 2.4452. Min Act: -0.0002

Data Index: 701833 (C4 (Web Text))

Max Activating Token Index: 683