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

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

Neuron 5530 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1607. Min Range: -2.1607

Max Act: 2.1607. Min Act: -0.0000

Data Index: 1370015 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 2.1607. Min Range: -2.1607

Max Act: 2.0584. Min Act: -0.0000

Data Index: 1426099 (Python Code)

Max Activating Token Index: 386

Text #2

Max Range: 2.1607. Min Range: -2.1607

Max Act: 2.0469. Min Act: -0.0000

Data Index: 1422259 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.9273. Min Act: -0.0000

Data Index: 1522678 (Python Code)

Max Activating Token Index: 378

Text #4

Max Range: 2.1607. Min Range: -2.1607

Max Act: 2.0228. Min Act: -0.0000

Data Index: 1596981 (Python Code)

Max Activating Token Index: 343

Text #5

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1652387 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8742. Min Act: -0.0000

Data Index: 1555963 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8978. Min Act: -0.0000

Data Index: 1385591 (Python Code)

Max Activating Token Index: 713

Text #8

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.7950. Min Act: -0.0000

Data Index: 1493489 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 2.1607. Min Range: -2.1607

Max Act: 2.0197. Min Act: -0.0000

Data Index: 1534046 (Python Code)

Max Activating Token Index: 894

Text #10

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.9575. Min Act: -0.0000

Data Index: 1619457 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8541. Min Act: -0.0000

Data Index: 1478514 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8572. Min Act: -0.0000

Data Index: 1517535 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8384. Min Act: -0.0000

Data Index: 1387765 (Python Code)

Max Activating Token Index: 700

Text #14

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8182. Min Act: -0.0000

Data Index: 1416933 (Python Code)

Max Activating Token Index: 484

Text #15

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1369500 (Python Code)

Max Activating Token Index: 252

Text #16

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8016. Min Act: -0.0000

Data Index: 1606757 (Python Code)

Max Activating Token Index: 644

Text #17

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.7882. Min Act: -0.0000

Data Index: 1504341 (Python Code)

Max Activating Token Index: 808

Text #18

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.7890. Min Act: -0.0000

Data Index: 1437076 (Python Code)

Max Activating Token Index: 372

Text #19

Max Range: 2.1607. Min Range: -2.1607

Max Act: 1.8870. Min Act: -0.0000

Data Index: 1495788 (Python Code)

Max Activating Token Index: 560