Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 746 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.6855. Min Act: -0.0001
Data Index: 1563146 (Python Code)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.7691. Min Act: -0.0001
Data Index: 1365931 (Python Code)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.8402. Min Act: -0.0001
Data Index: 1509208 (Python Code)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.7392. Min Act: -0.0001
Data Index: 1513682 (Python Code)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.6927. Min Act: -0.0001
Data Index: 1634021 (Python Code)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.6931. Min Act: -0.0001
Data Index: 1558864 (Python Code)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.7777. Min Act: -0.0001
Data Index: 1504233 (Python Code)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.4882. Min Act: -0.0001
Data Index: 1457031 (Python Code)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.6718. Min Act: -0.0001
Data Index: 1423884 (Python Code)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.6424. Min Act: -0.0001
Data Index: 1509927 (Python Code)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.6086. Min Act: -0.0001
Data Index: 1381761 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.6147. Min Act: -0.0001
Data Index: 1600227 (Python Code)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.5732. Min Act: -0.0002
Data Index: 1437936 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.8381. Min Act: -0.0001
Data Index: 1428379 (Python Code)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.5762. Min Act: -0.0001
Data Index: 1398852 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.4886. Min Act: -0.0001
Data Index: 1482401 (Python Code)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.5803. Min Act: -0.0001
Data Index: 1403454 (Python Code)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.5501. Min Act: -0.0001
Data Index: 1618212 (Python Code)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.5423. Min Act: -0.0001
Data Index: 1586830 (Python Code)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8402. Min Range: -1.8402
Max Act: 1.6534. Min Act: -0.0001
Data Index: 1410636 (Python Code)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19