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

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

Neuron 3695 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: 1.6352. Min Range: -1.6352

Max Act: 1.6352. Min Act: -0.0002

Data Index: 1533246 (Python Code)

Max Activating Token Index: 288

Text #1

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.5086. Min Act: -0.0002

Data Index: 1615942 (Python Code)

Max Activating Token Index: 431

Text #2

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.5084. Min Act: -0.0002

Data Index: 1489021 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.4346. Min Act: -0.0002

Data Index: 1545618 (Python Code)

Max Activating Token Index: 423

Text #4

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.3685. Min Act: -0.0002

Data Index: 1601609 (Python Code)

Max Activating Token Index: 332

Text #5

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.2808. Min Act: -0.0002

Data Index: 1563383 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.3962. Min Act: -0.0002

Data Index: 1500348 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.2717. Min Act: -0.0002

Data Index: 1530619 (Python Code)

Max Activating Token Index: 1020

Text #8

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.2335. Min Act: -0.0002

Data Index: 1416984 (Python Code)

Max Activating Token Index: 662

Text #9

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.4058. Min Act: -0.0002

Data Index: 1475150 (Python Code)

Max Activating Token Index: 238

Text #10

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.2129. Min Act: -0.0002

Data Index: 1570928 (Python Code)

Max Activating Token Index: 164

Text #11

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.2778. Min Act: -0.0002

Data Index: 1493849 (Python Code)

Max Activating Token Index: 398

Text #12

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.2586. Min Act: -0.0002

Data Index: 1580450 (Python Code)

Max Activating Token Index: 464

Text #13

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.1458. Min Act: -0.0002

Data Index: 1531784 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.3487. Min Act: -0.0002

Data Index: 1596075 (Python Code)

Max Activating Token Index: 395

Text #15

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.2783. Min Act: -0.0002

Data Index: 1451328 (Python Code)

Max Activating Token Index: 365

Text #16

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.2596. Min Act: -0.0002

Data Index: 1613764 (Python Code)

Max Activating Token Index: 474

Text #17

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.2361. Min Act: -0.0002

Data Index: 1601944 (Python Code)

Max Activating Token Index: 335

Text #18

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.3376. Min Act: -0.0002

Data Index: 1536484 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 1.6352. Min Range: -1.6352

Max Act: 1.1950. Min Act: -0.0002

Data Index: 1554902 (Python Code)

Max Activating Token Index: 921