Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1314 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.3840. Min Act: -0.0000

Data Index: 1571090 (Python Code)

Max Activating Token Index: 998

Text #1

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.4104. Min Act: -0.0000

Data Index: 1500245 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.3847. Min Act: -0.0000

Data Index: 1364174 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.4141. Min Act: -0.0000

Data Index: 1520266 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.3643. Min Act: -0.0000

Data Index: 1463656 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1585752 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.3800. Min Act: -0.0000

Data Index: 1476994 (Python Code)

Max Activating Token Index: 175

Text #7

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.3210. Min Act: -0.0000

Data Index: 1385592 (Python Code)

Max Activating Token Index: 214

Text #8

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1568384 (Python Code)

Max Activating Token Index: 969

Text #9

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.2668. Min Act: -0.0000

Data Index: 1496100 (Python Code)

Max Activating Token Index: 578

Text #10

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.2191. Min Act: -0.0000

Data Index: 1487322 (Python Code)

Max Activating Token Index: 592

Text #11

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.3815. Min Act: -0.0000

Data Index: 1576505 (Python Code)

Max Activating Token Index: 908

Text #12

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.2492. Min Act: -0.0000

Data Index: 1399132 (Python Code)

Max Activating Token Index: 813

Text #13

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1615399 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.2774. Min Act: -0.0000

Data Index: 1402785 (Python Code)

Max Activating Token Index: 923

Text #15

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1421909 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.1748. Min Act: -0.0000

Data Index: 1434735 (Python Code)

Max Activating Token Index: 56

Text #17

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1376580 (Python Code)

Max Activating Token Index: 712

Text #18

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1557981 (Python Code)

Max Activating Token Index: 402

Text #19

Max Range: 1.4141. Min Range: -1.4141

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1611953 (Python Code)

Max Activating Token Index: 758