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

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

Neuron 1164 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.6062. Min Act: -0.0002

Data Index: 329841 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5908. Min Act: -0.0002

Data Index: 1194252 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5998. Min Act: -0.0002

Data Index: 1410473 (Python Code)

Max Activating Token Index: 413

Text #3

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5761. Min Act: -0.0002

Data Index: 1479810 (Python Code)

Max Activating Token Index: 18

Text #4

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.6020. Min Act: -0.0002

Data Index: 159097 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5745. Min Act: -0.0002

Data Index: 1467055 (Python Code)

Max Activating Token Index: 933

Text #6

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5569. Min Act: -0.0002

Data Index: 1486993 (Python Code)

Max Activating Token Index: 137

Text #7

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5537. Min Act: -0.0002

Data Index: 1542612 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5535. Min Act: -0.0002

Data Index: 1641321 (Python Code)

Max Activating Token Index: 678

Text #9

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5451. Min Act: -0.0002

Data Index: 1566514 (Python Code)

Max Activating Token Index: 115

Text #10

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5531. Min Act: -0.0002

Data Index: 1653985 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5509. Min Act: -0.0002

Data Index: 1441401 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5420. Min Act: -0.0002

Data Index: 1646001 (Python Code)

Max Activating Token Index: 879

Text #13

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5366. Min Act: -0.0002

Data Index: 1523775 (Python Code)

Max Activating Token Index: 651

Text #14

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5482. Min Act: -0.0002

Data Index: 1550621 (Python Code)

Max Activating Token Index: 399

Text #15

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5419. Min Act: -0.0002

Data Index: 1434578 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5368. Min Act: -0.0002

Data Index: 1432532 (Python Code)

Max Activating Token Index: 825

Text #17

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5267. Min Act: -0.0002

Data Index: 1555325 (Python Code)

Max Activating Token Index: 488

Text #18

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5291. Min Act: -0.0002

Data Index: 1512785 (Python Code)

Max Activating Token Index: 540

Text #19

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5254. Min Act: -0.0002

Data Index: 1589241 (Python Code)

Max Activating Token Index: 144