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

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

Neuron 1670 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3640. Min Act: -0.0001

Data Index: 1383239 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5231. Min Act: -0.0001

Data Index: 1590228 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5017. Min Act: -0.0001

Data Index: 1385498 (Python Code)

Max Activating Token Index: 588

Text #3

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1494874 (Python Code)

Max Activating Token Index: 683

Text #4

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1468706 (Python Code)

Max Activating Token Index: 523

Text #5

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4577. Min Act: -0.0001

Data Index: 1641002 (Python Code)

Max Activating Token Index: 505

Text #6

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4226. Min Act: -0.0001

Data Index: 1475248 (Python Code)

Max Activating Token Index: 622

Text #7

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4732. Min Act: -0.0001

Data Index: 1449705 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1608168 (Python Code)

Max Activating Token Index: 751

Text #9

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4200. Min Act: -0.0001

Data Index: 1651356 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4202. Min Act: -0.0001

Data Index: 1642515 (Python Code)

Max Activating Token Index: 580

Text #11

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4338. Min Act: -0.0001

Data Index: 1589048 (Python Code)

Max Activating Token Index: 519

Text #12

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1512416 (Python Code)

Max Activating Token Index: 283

Text #13

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4995. Min Act: -0.0001

Data Index: 1461562 (Python Code)

Max Activating Token Index: 690

Text #14

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1479269 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.2878. Min Act: -0.0001

Data Index: 1632086 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1627429 (Python Code)

Max Activating Token Index: 636

Text #17

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.4093. Min Act: -0.0001

Data Index: 1417168 (Python Code)

Max Activating Token Index: 1017

Text #18

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1568179 (Python Code)

Max Activating Token Index: 650

Text #19

Max Range: 0.5890. Min Range: -0.5890

Max Act: 0.3013. Min Act: -0.0000

Data Index: 1378784 (Python Code)

Max Activating Token Index: 859