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

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

Neuron 2408 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8195. Min Range: -4.8195

Max Act: 4.8195. Min Act: -0.0000

Data Index: 1560752 (Python Code)

Max Activating Token Index: 773

Text #1

Max Range: 4.8195. Min Range: -4.8195

Max Act: 4.4609. Min Act: -0.0000

Data Index: 1436587 (Python Code)

Max Activating Token Index: 412

Text #2

Max Range: 4.8195. Min Range: -4.8195

Max Act: 4.1764. Min Act: -0.0000

Data Index: 1547024 (Python Code)

Max Activating Token Index: 406

Text #3

Max Range: 4.8195. Min Range: -4.8195

Max Act: 4.0086. Min Act: -0.0000

Data Index: 1621575 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 4.8195. Min Range: -4.8195

Max Act: 4.1510. Min Act: -0.0000

Data Index: 1371831 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 4.8195. Min Range: -4.8195

Max Act: 4.1559. Min Act: -0.0000

Data Index: 1527344 (Python Code)

Max Activating Token Index: 1015

Text #6

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.8105. Min Act: -0.0000

Data Index: 1641597 (Python Code)

Max Activating Token Index: 642

Text #7

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.9259. Min Act: -0.0000

Data Index: 1486053 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 4.8195. Min Range: -4.8195

Max Act: 4.0041. Min Act: -0.0000

Data Index: 1434037 (Python Code)

Max Activating Token Index: 991

Text #9

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.8406. Min Act: -0.0000

Data Index: 1572949 (Python Code)

Max Activating Token Index: 831

Text #10

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.7974. Min Act: -0.0000

Data Index: 1643879 (Python Code)

Max Activating Token Index: 391

Text #11

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.7719. Min Act: -0.0000

Data Index: 1570958 (Python Code)

Max Activating Token Index: 286

Text #12

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.7354. Min Act: -0.0000

Data Index: 1509378 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.7180. Min Act: -0.0000

Data Index: 1481680 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.8474. Min Act: -0.0000

Data Index: 1570260 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.4533. Min Act: -0.0000

Data Index: 1655234 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.5879. Min Act: -0.0000

Data Index: 1361127 (Python Code)

Max Activating Token Index: 883

Text #17

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.7275. Min Act: -0.0000

Data Index: 1608673 (Python Code)

Max Activating Token Index: 840

Text #18

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.5476. Min Act: -0.0000

Data Index: 1479800 (Python Code)

Max Activating Token Index: 678

Text #19

Max Range: 4.8195. Min Range: -4.8195

Max Act: 3.3733. Min Act: -0.0000

Data Index: 1642640 (Python Code)

Max Activating Token Index: 384