Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3800 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0490. Min Act: -0.0002

Data Index: 918979 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 514654 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1619415 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1445119 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0500. Min Act: -0.0002

Data Index: 519834 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0440. Min Act: -0.0002

Data Index: 1578289 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0453. Min Act: -0.0002

Data Index: 525630 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0444. Min Act: -0.0002

Data Index: 250434 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1025151 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0495. Min Act: -0.0002

Data Index: 975374 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1507495 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1020714 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0423. Min Act: -0.0002

Data Index: 322716 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0381. Min Act: -0.0002

Data Index: 672067 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1016242 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0443. Min Act: -0.0002

Data Index: 58059 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1002600 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0407. Min Act: -0.0002

Data Index: 717862 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0418. Min Act: -0.0002

Data Index: 493545 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0415. Min Act: -0.0002

Data Index: 567661 (C4 (Web Text))

Max Activating Token Index: 253