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

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

Neuron 1555 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1478995 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1544479 (Python Code)

Max Activating Token Index: 778

Text #2

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.2520. Min Act: -0.0000

Data Index: 1559243 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.3909. Min Act: -0.0000

Data Index: 1622566 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.3502. Min Act: -0.0000

Data Index: 1576048 (Python Code)

Max Activating Token Index: 781

Text #5

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.2100. Min Act: -0.0000

Data Index: 1562088 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1463548 (Python Code)

Max Activating Token Index: 288

Text #7

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1620825 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.1973. Min Act: -0.0000

Data Index: 1391145 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 1.3909. Min Range: -1.3909

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1525484 (Python Code)

Max Activating Token Index: 795

Text #10

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.1616. Min Act: -0.0000

Data Index: 1478190 (Python Code)

Max Activating Token Index: 306

Text #11

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1473012 (Python Code)

Max Activating Token Index: 181

Text #12

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1429730 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1526720 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1561472 (Python Code)

Max Activating Token Index: 269

Text #15

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1540106 (Python Code)

Max Activating Token Index: 174

Text #16

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1545030 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 1.3909. Min Range: -1.3909

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1633896 (Python Code)

Max Activating Token Index: 946

Text #18

Max Range: 1.3909. Min Range: -1.3909

Max Act: 0.9964. Min Act: -0.0000

Data Index: 1548391 (Python Code)

Max Activating Token Index: 673

Text #19

Max Range: 1.3909. Min Range: -1.3909

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1613736 (Python Code)

Max Activating Token Index: 648