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

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

Neuron 4424 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2488. Min Range: -2.2488

Max Act: 2.2488. Min Act: -0.0000

Data Index: 1402215 (Python Code)

Max Activating Token Index: 668

Text #1

Max Range: 2.2488. Min Range: -2.2488

Max Act: 2.1996. Min Act: -0.0000

Data Index: 1433474 (Python Code)

Max Activating Token Index: 693

Text #2

Max Range: 2.2488. Min Range: -2.2488

Max Act: 2.0517. Min Act: -0.0000

Data Index: 1593751 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9043. Min Act: -0.0001

Data Index: 1447204 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9942. Min Act: -0.0000

Data Index: 1648135 (Python Code)

Max Activating Token Index: 548

Text #5

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.8735. Min Act: -0.0000

Data Index: 1426729 (Python Code)

Max Activating Token Index: 249

Text #6

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9472. Min Act: -0.0000

Data Index: 1481278 (Python Code)

Max Activating Token Index: 477

Text #7

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9361. Min Act: -0.0001

Data Index: 1567385 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9769. Min Act: -0.0000

Data Index: 1569398 (Python Code)

Max Activating Token Index: 145

Text #9

Max Range: 2.2488. Min Range: -2.2488

Max Act: 2.0346. Min Act: -0.0000

Data Index: 1489170 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 2.2488. Min Range: -2.2488

Max Act: 2.0372. Min Act: -0.0001

Data Index: 1571906 (Python Code)

Max Activating Token Index: 674

Text #11

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.8898. Min Act: -0.0000

Data Index: 1452684 (Python Code)

Max Activating Token Index: 479

Text #12

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.8716. Min Act: -0.0000

Data Index: 1557869 (Python Code)

Max Activating Token Index: 413

Text #13

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.9255. Min Act: -0.0000

Data Index: 1563067 (Python Code)

Max Activating Token Index: 287

Text #14

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.7837. Min Act: -0.0000

Data Index: 1547069 (Python Code)

Max Activating Token Index: 216

Text #15

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.7965. Min Act: -0.0001

Data Index: 1583713 (Python Code)

Max Activating Token Index: 802

Text #16

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1383804 (Python Code)

Max Activating Token Index: 750

Text #17

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.7502. Min Act: -0.0000

Data Index: 1467839 (Python Code)

Max Activating Token Index: 451

Text #18

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.7549. Min Act: -0.0000

Data Index: 1469283 (Python Code)

Max Activating Token Index: 452

Text #19

Max Range: 2.2488. Min Range: -2.2488

Max Act: 1.7522. Min Act: -0.0000

Data Index: 1362272 (Python Code)

Max Activating Token Index: 608