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

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

Neuron 1681 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1693. Min Range: -2.1693

Max Act: 2.1693. Min Act: -0.0000

Data Index: 1371839 (Python Code)

Max Activating Token Index: 409

Text #1

Max Range: 2.1693. Min Range: -2.1693

Max Act: 2.0254. Min Act: -0.0000

Data Index: 1465919 (Python Code)

Max Activating Token Index: 104

Text #2

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.8349. Min Act: -0.0000

Data Index: 1591560 (Python Code)

Max Activating Token Index: 680

Text #3

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.5043. Min Act: -0.0000

Data Index: 1549752 (Python Code)

Max Activating Token Index: 359

Text #4

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.6157. Min Act: -0.0000

Data Index: 1361640 (Python Code)

Max Activating Token Index: 334

Text #5

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1426488 (Python Code)

Max Activating Token Index: 237

Text #6

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1647917 (Python Code)

Max Activating Token Index: 493

Text #7

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1376008 (Python Code)

Max Activating Token Index: 312

Text #8

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.4114. Min Act: -0.0000

Data Index: 1587664 (Python Code)

Max Activating Token Index: 1004

Text #9

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1443636 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3813. Min Act: -0.0000

Data Index: 1396918 (Python Code)

Max Activating Token Index: 878

Text #11

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1467235 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3585. Min Act: -0.0000

Data Index: 1616895 (Python Code)

Max Activating Token Index: 909

Text #13

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3432. Min Act: -0.0000

Data Index: 1583906 (Python Code)

Max Activating Token Index: 927

Text #14

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3453. Min Act: -0.0000

Data Index: 1572990 (Python Code)

Max Activating Token Index: 766

Text #15

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3520. Min Act: -0.0000

Data Index: 1482620 (Python Code)

Max Activating Token Index: 925

Text #16

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1463757 (Python Code)

Max Activating Token Index: 372

Text #17

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.4101. Min Act: -0.0000

Data Index: 1422063 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3169. Min Act: -0.0000

Data Index: 1603048 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 2.1693. Min Range: -2.1693

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1388706 (Python Code)

Max Activating Token Index: 212