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

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

Neuron 4338 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: 1.4517. Min Range: -1.4517

Max Act: 1.4517. Min Act: -0.0002

Data Index: 825114 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.4166. Min Act: -0.0002

Data Index: 729487 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3718. Min Act: -0.0002

Data Index: 256251 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3870. Min Act: -0.0002

Data Index: 1136717 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3711. Min Act: -0.0002

Data Index: 920296 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3455. Min Act: -0.0002

Data Index: 912605 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3407. Min Act: -0.0002

Data Index: 1026825 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.3472. Min Act: -0.0002

Data Index: 481789 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2804. Min Act: -0.0002

Data Index: 738129 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2646. Min Act: -0.0002

Data Index: 1001969 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2912. Min Act: -0.0002

Data Index: 743811 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2633. Min Act: -0.0002

Data Index: 917515 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2661. Min Act: -0.0002

Data Index: 683568 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2650. Min Act: -0.0002

Data Index: 963590 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2513. Min Act: -0.0002

Data Index: 328775 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2368. Min Act: -0.0002

Data Index: 920239 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2339. Min Act: -0.0002

Data Index: 318201 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2920. Min Act: -0.0002

Data Index: 491277 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2750. Min Act: -0.0002

Data Index: 118123 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.4517. Min Range: -1.4517

Max Act: 1.2522. Min Act: -0.0002

Data Index: 1256668 (C4 (Web Text))

Max Activating Token Index: 4