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

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

Neuron 5802 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.6437. Min Act: -0.0002

Data Index: 856482 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.4376. Min Act: -0.0002

Data Index: 322124 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.1563. Min Act: -0.0002

Data Index: 24823 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.1931. Min Act: -0.0002

Data Index: 495454 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.1199. Min Act: -0.0001

Data Index: 961338 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.1385. Min Act: -0.0002

Data Index: 343520 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.1242. Min Act: -0.0002

Data Index: 278040 (C4 (Web Text))

Max Activating Token Index: 378

Text #7

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.0664. Min Act: -0.0002

Data Index: 1258111 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.0332. Min Act: -0.0001

Data Index: 165822 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.0789. Min Act: -0.0002

Data Index: 1160764 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.0447. Min Act: -0.0002

Data Index: 264033 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.0080. Min Act: -0.0002

Data Index: 971312 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 1.6437. Min Range: -1.6437

Max Act: 1.0299. Min Act: -0.0002

Data Index: 1084701 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 1.6437. Min Range: -1.6437

Max Act: 0.9830. Min Act: -0.0002

Data Index: 1298518 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.6437. Min Range: -1.6437

Max Act: 0.9929. Min Act: -0.0002

Data Index: 837504 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.6437. Min Range: -1.6437

Max Act: 0.9653. Min Act: -0.0002

Data Index: 777447 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.6437. Min Range: -1.6437

Max Act: 0.9898. Min Act: -0.0001

Data Index: 456937 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.6437. Min Range: -1.6437

Max Act: 0.9605. Min Act: -0.0002

Data Index: 6211 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 1.6437. Min Range: -1.6437

Max Act: 0.9784. Min Act: -0.0002

Data Index: 102865 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.6437. Min Range: -1.6437

Max Act: 0.9774. Min Act: -0.0002

Data Index: 1016359 (C4 (Web Text))

Max Activating Token Index: 377