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

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

Neuron 2853 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1720. Min Range: -2.1720

Max Act: 2.1720. Min Act: -0.0000

Data Index: 1435875 (Python Code)

Max Activating Token Index: 662

Text #1

Max Range: 2.1720. Min Range: -2.1720

Max Act: 2.1355. Min Act: -0.0000

Data Index: 1631724 (Python Code)

Max Activating Token Index: 954

Text #2

Max Range: 2.1720. Min Range: -2.1720

Max Act: 2.1258. Min Act: -0.0000

Data Index: 1590065 (Python Code)

Max Activating Token Index: 614

Text #3

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.9742. Min Act: -0.0000

Data Index: 1480076 (Python Code)

Max Activating Token Index: 925

Text #4

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.8563. Min Act: -0.0000

Data Index: 1527468 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.8761. Min Act: -0.0000

Data Index: 1619602 (Python Code)

Max Activating Token Index: 627

Text #6

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.7661. Min Act: -0.0000

Data Index: 1542401 (Python Code)

Max Activating Token Index: 523

Text #7

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.7662. Min Act: -0.0000

Data Index: 1533525 (Python Code)

Max Activating Token Index: 571

Text #8

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.8643. Min Act: -0.0000

Data Index: 1363928 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.8367. Min Act: -0.0000

Data Index: 1439366 (Python Code)

Max Activating Token Index: 1002

Text #10

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.8234. Min Act: -0.0000

Data Index: 1495913 (Python Code)

Max Activating Token Index: 178

Text #11

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.8098. Min Act: -0.0000

Data Index: 1429958 (Python Code)

Max Activating Token Index: 366

Text #12

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.8382. Min Act: -0.0000

Data Index: 1501018 (Python Code)

Max Activating Token Index: 229

Text #13

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.7934. Min Act: -0.0000

Data Index: 1477988 (Python Code)

Max Activating Token Index: 489

Text #14

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1586056 (Python Code)

Max Activating Token Index: 805

Text #15

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1508395 (Python Code)

Max Activating Token Index: 702

Text #16

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1564032 (Python Code)

Max Activating Token Index: 353

Text #17

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.6119. Min Act: -0.0000

Data Index: 1375116 (Python Code)

Max Activating Token Index: 957

Text #18

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1421085 (Python Code)

Max Activating Token Index: 1010

Text #19

Max Range: 2.1720. Min Range: -2.1720

Max Act: 1.6918. Min Act: -0.0000

Data Index: 1603445 (Python Code)

Max Activating Token Index: 650